CN115205740B - Body-building exercise auxiliary teaching method and system - Google Patents
Body-building exercise auxiliary teaching method and system Download PDFInfo
- Publication number
- CN115205740B CN115205740B CN202210806144.0A CN202210806144A CN115205740B CN 115205740 B CN115205740 B CN 115205740B CN 202210806144 A CN202210806144 A CN 202210806144A CN 115205740 B CN115205740 B CN 115205740B
- Authority
- CN
- China
- Prior art keywords
- information
- action
- beat
- standard
- reminding
- 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.)
- Active
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06V20/48—Matching video sequences
-
- 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
Abstract
The invention discloses a gymnastics auxiliary teaching method and a gymnastics auxiliary teaching system, which relate to the field of physical education, wherein the method comprises the following steps: obtaining first video information through the video acquisition device; obtaining a standard action of a first body-building exercise and standard beat information matched with the standard action; constructing a body-building operation evaluation model; according to the first video information, performing traversal feature extraction on the action of each person in each frame of the video to obtain a first action set; obtaining beat information corresponding to each action information in the first action set; inputting each action information in the first action set and beat information corresponding to each action information into the fitness operation evaluation model to obtain a first evaluation result; and analyzing the first evaluation result to obtain first reminding information, wherein the first reminding information is used for assisting a teacher in performing gymnastics teaching.
Description
Technical Field
The invention relates to the field of physical education teaching, in particular to a gymnastics auxiliary teaching method and system.
Background
The gymnastics is a novel sports item integrating factors such as gymnastics, music, dancing and aesthetic feelings, the music is vigorous, the rhythmicity and the rhythm are strong, and the actions are natural, elegant and beautiful and are varied. With the continuous development of the current society, people begin to choose more diversified life styles. The gymnastics attracts countless people's eyes by the action of music with clear rhythm and rhythmic body movement. People can exercise physical fitness, shape body and grind mind while doing exercises, and the exercise machine has important significance for comprehensive development of people.
In the prior art, the problem that the teaching effect of the gymnastics is poor due to the lack of timely and efficient reminding for the wrong actions of the gymnastics exists.
Disclosure of Invention
The application provides a gymnastics auxiliary teaching method and system, and solves the technical problem that the teaching effect of gymnastics is poor due to the fact that timely and efficient reminding is lacked for the wrong actions of gymnastics in the prior art.
In view of the above problems, the present application provides a gymnastics assistant teaching method and system.
In one aspect, the present application provides a gymnastics auxiliary teaching method, wherein the method is applied to a gymnastics auxiliary teaching system, the system comprises a video acquisition device, and the method comprises: acquiring first video information through the video acquisition device, wherein the first video information comprises video information of a plurality of persons performing gymnastics; obtaining a standard action of a first body-building exercise and standard beat information matched with the standard action; training a neural network model according to the standard action and the standard beat information, and constructing a gymnastics action evaluation model; performing traversal feature extraction on the action of each person in each frame of the video according to the first video information to obtain a first action set, wherein the first action set comprises the action information of each person in each frame; obtaining beat information corresponding to each piece of action information in the first action set according to the standard beat information; inputting each action information in the first action set and beat information corresponding to each action information into the exercise action evaluation model to obtain a first evaluation result, wherein the first evaluation result comprises wrong action information and wrong beat information in the first video information; and analyzing the first evaluation result to obtain first reminding information, wherein the first reminding information is used for assisting a teacher in performing gymnastics teaching.
On the other hand, this application still provides a body-building exercises auxiliary teaching system, the system includes video acquisition device, wherein, the system still includes: the first obtaining unit is used for obtaining first video information through the video collecting device, and the first video information comprises video information of a plurality of persons performing gymnastics; the second obtaining unit is used for obtaining the standard motions of the first body-building exercises and the standard beat information matched with the standard motions; the first execution unit is used for training a neural network model according to the standard action and the standard beat information to construct a gymnastics action evaluation model; a third obtaining unit, configured to perform traversal feature extraction on an action of each person in each frame of the video according to the first video information, and obtain a first action set, where the first action set includes action information of each person in each frame; a fourth obtaining unit, configured to obtain, according to the standard beat information, beat information corresponding to each piece of action information in the first action set; a fifth obtaining unit, configured to input each piece of motion information in the first motion set and beat information corresponding to each piece of motion information into the exercise operation evaluation model to obtain a first evaluation result, where the first evaluation result includes wrong motion information and wrong beat information in the first video information; and the sixth obtaining unit is used for analyzing the first evaluation result to obtain first reminding information, and the first reminding information is used for assisting a teacher in performing gymnastics teaching.
In a third aspect, the present application provides a gymnastic teaching aid system, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium, wherein the storage medium has stored thereon a computer program which, when executed by a processor, implements the method of any of the first aspects described above.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
acquiring first video information through a video acquisition device; acquiring standard motions of a first gymnastics and standard beat information matched with the standard motions; further, training the neural network model, and constructing a gymnastics action evaluation model; performing traversal feature extraction on the action of each person in each frame in the first video information to obtain a first action set; further, beat information corresponding to each piece of action information in the first action set is obtained; inputting each action information in the first action set and beat information corresponding to each action information into the fitness operation evaluation model to obtain a first evaluation result; and analyzing the first reminding information to obtain first reminding information to assist a teacher in performing gymnastics teaching. Timely and efficient reminding of the error actions of the gymnastics is achieved; the teaching effect of the gymnastics is improved; optimizing a teaching method of the gymnastics; improving the teaching and evaluation system of the gymnastics; meanwhile, an intelligent fitness operation evaluation model is designed to assist teachers in fitness exercise teaching, so that the energy and physical strength of the teachers are saved; help students to master the knowledge and skill of gymnastics; the technical effect of deepening the understanding of students on the essential characteristics of the gymnastics is achieved.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without inventive effort.
FIG. 1 is a schematic flow chart of a gymnastics teaching aid method according to the present application;
fig. 2 is a schematic flow chart illustrating a process of analyzing the first evaluation result to obtain the first reminding information in the gymnastics assistant teaching method according to the present application;
FIG. 3 is a schematic flow chart illustrating a method for assisting in teaching gymnastics according to the present application, wherein a plurality of people are reminded of a multi-type error occurring in a first frame;
FIG. 4 is a schematic structural diagram of an exercise assistant teaching system according to the present application;
fig. 5 is a schematic structural diagram of an exemplary electronic device of the present application.
Detailed Description
By providing the gymnastics auxiliary teaching method and system, the technical problem that the teaching effect of the gymnastics is poor due to the fact that timely and efficient reminding is lacked for the wrong actions of the gymnastics in the prior art is solved. Timely and efficient reminding of the error actions of the gymnastics is achieved; the teaching effect of the gymnastics is improved; optimizing a teaching method of the gymnastics; improving the teaching and evaluation system of the gymnastics; meanwhile, an intelligent fitness operation evaluation model is designed to assist teachers in fitness exercise teaching, so that the energy and physical strength of the teachers are saved; help students to master the knowledge and skill of gymnastics; the technical effect of deepening the understanding of students on the essential characteristics of the gymnastics is achieved.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
The gymnastics is a novel sports item integrating factors such as gymnastics, music, dancing and aesthetic feelings, the music is vigorous, the rhythmicity and the rhythm are strong, and the actions are natural, elegant and beautiful and are varied. With the continuous development of the current society, people begin to choose more diversified life styles. The gymnastics attracts countless people's eyes by the action of music with clear rhythm and rhythmic body movement. People can exercise physical fitness, shape body and develop mentality while doing exercises, and the exercise machine has important significance for comprehensive development of people.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the application provides a gymnastics auxiliary teaching method, wherein the method is applied to a gymnastics auxiliary teaching system, the system comprises a video acquisition device, and the method comprises the following steps: acquiring first video information through a video acquisition device; obtaining standard motions of a first body-building exercise and standard beat information matched with the standard motions; further, training the neural network model, and constructing a gymnastics action evaluation model; performing traversal feature extraction on the action of each person in each frame in the first video information to obtain a first action set; further, beat information corresponding to each piece of action information in the first action set is obtained; inputting each action information in the first action set and beat information corresponding to each action information into the fitness operation evaluation model to obtain a first evaluation result; and analyzing the first reminding information to obtain first reminding information to assist a teacher in performing gymnastics teaching.
For better understanding of the above technical solutions, the following detailed descriptions will be provided in conjunction with the drawings and the detailed description of the embodiments.
Example one
Referring to fig. 1, the present application provides a gymnastics assistant teaching method, wherein the method is applied to a gymnastics assistant teaching system, the system includes a video acquisition device, and the method specifically includes the following steps:
step S100: acquiring first video information through the video acquisition device, wherein the first video information comprises video information of a plurality of persons performing gymnastics;
step S200: obtaining a standard action of a first body-building exercise and standard beat information matched with the standard action;
specifically, the existing video monitoring system has the limitations and disadvantages of short transmission distance, easy distortion of videos, poor system expansibility, difficult integration among systems and the like. Preferably, the video acquisition device is adopted to acquire the gymnastics and sports video information of the user. The video acquisition device acquires first video information, the first video information is any video information of any person performing gymnastics, the any person comprises a single person and a plurality of persons, and the gymnastics comprise various gymnastics such as aerobic gymnastics, office gymnastics, latin gymnastics, fighting gymnastics, leg-slimming exercises and face-slimming exercises. Further, standard motions of the first gymnastics and standard beat information matched with the standard motions are obtained. The standard motion information of the first gymnastics is the standard motion information of any person performing any gymnastics, for example, when the person performs bouncing and kicking leg jumping, the standard motion information of the demonstration person is that the right foot is lifted and bent, and the left foot is lifted and bounced while the right knee is straightened and kicked forwards; then the right foot falls to the ground while the left leg bends backwards, and the opposite direction or the next action is followed. When kicking the leg, the thigh exerts force first, and then the shank stretches, the knee joint is not rigid, and the leg stretches forwards and downwards under the control. And the standard beat information matched with the standard action is beat information corresponding to the standard action. For example, when kicking a leg, the first beat performs a right foot lifting and bending backward, the second beat performs a left foot lifting and a right knee straightening and kicking forward, and the third beat performs beat information such as a right foot landing and a left leg bending backward. The technical effects of collecting the first video information, obtaining the standard action of the first gymnastics and the standard beat information matched with the standard action, and laying a foundation for subsequently constructing a gymnastics action evaluation model and obtaining the first action set are achieved.
Step S300: training a neural network model according to the standard action and the standard beat information, and constructing a gymnastics action evaluation model;
step S400: performing traversal feature extraction on the action of each person in each frame of the video according to the first video information to obtain a first action set, wherein the first action set comprises the action information of each person in each frame;
step S500: obtaining beat information corresponding to each piece of action information in the first action set according to the standard beat information;
specifically, the teaching evaluation is to perform quantitative and qualitative value judgment on the teaching quality according to a teaching target and a value scale. The assessment of the aerobics exercises is mainly performed by technical evaluation, the standard actions in the eyes of the referees are high-quality actions, and different referees give different scores for the same set of actions of the same person. The action evaluation system of aerobics exercises needs to be improved and perfected. Preferably, the exercise operation evaluation model is adopted to objectively evaluate exercise operation information of the user and beat information corresponding to each action information. The body-building operation evaluation model is a neural network model obtained by training the neural network model through the standard operation and the standard beat information, and has the characteristics of the neural network model. The neural network model is a neural network model in machine learning, reflects many basic characteristics of human brain functions, is a deep feedforward neural network with the characteristics of local connection, weight sharing and the like, and is a highly complex nonlinear dynamical learning system. Further, according to the first video information, traversal feature extraction of the action of each person in each frame of the video is carried out, and a first action set is obtained. The first action set is composed of action information for each person in each frame of the first video information. For example, any person may perform fitness operation information such as kicking, push-up, sit-up, and the like. And then, obtaining beat information corresponding to each piece of action information in the first action set on the basis of obtaining the standard beat information. For example, when the kicking leg is bounced, the standard beat information is that the first beat is subjected to right foot lifting and backward bending, and beat information actually corresponding to the right foot lifting and backward bending of any person when the kicking leg is bounced is obtained. The technical effects that the exercise movement evaluation model is built, each movement information in the first movement set and the beat information corresponding to each movement information are obtained, and data support is provided for assisting teachers to conduct exercise teaching through the exercise movement evaluation model in the follow-up process are achieved.
Step S600: inputting each action information in the first action set and beat information corresponding to each action information into the exercise action evaluation model to obtain a first evaluation result, wherein the first evaluation result comprises wrong action information and wrong beat information in the first video information;
step S700: and analyzing the first evaluation result to obtain first reminding information, wherein the first reminding information is used for assisting a teacher in performing gymnastics teaching.
Specifically, each piece of motion information in the first motion set and beat information corresponding to each piece of motion information are used as input information, the exercise operation evaluation model is input, and the exercise operation evaluation model established based on the neural network model can output the first evaluation result. The first evaluation result is that the action information of each person in each frame in the first video information and the beat information corresponding to each action information are intelligently evaluated, and the first evaluation result comprises error action information and error beat information in the first video information. Further, first reminding information is obtained by analyzing the first evaluation result. The first reminding information is used for sending out reminding when the personnel have errors, and assisting a teacher in performing gymnastics teaching. Timely and efficient reminding of the error actions of the gymnastics is achieved; the teaching effect of the gymnastics is improved; optimizing a teaching method of the gymnastics; improving the teaching and evaluation system of the gymnastics; meanwhile, an intelligent fitness operation evaluation model is designed to assist teachers in fitness exercise teaching, so that the energy and physical strength of the teachers are saved; help students to master the knowledge and skill of gymnastics; the technical effect of deepening the understanding of students on the essential characteristics of the gymnastics is achieved.
Further, as shown in fig. 2, step S700 of the present application further includes:
step S710: obtaining first quantity information of the error actions in the first frame according to the first evaluation result;
step S720: judging whether the first quantity information is 0 or not;
step S730: if the first quantity information is not 0, judging whether the first quantity information is larger than 1;
step S740: and if the first quantity information is equal to 1, obtaining second reminding information, wherein the second reminding information is used for reminding a person of errors in the first frame.
Specifically, each frame of picture in the first evaluation result is analyzed to obtain first quantity information of the error actions in the first frame. And the first quantity information of the false actions in the first frame represents the quantity of people with false actions in any frame. Further, judging whether the first quantity information is 0; if not, judging whether the first quantity information is larger than 1 again; and if the first quantity information is equal to 1, sending second reminding information to remind a person of errors in the first frame. For example, if the number of people with a malfunction in one frame of picture is 1, the first number information of the malfunction in the first frame is 1, and a second reminding information is sent. The technical effect that the teacher is reminded that a person has errors in the first frame through the second reminding information to help the teacher to perform gymnastics teaching is achieved.
Further, as shown in fig. 3, step S730 of the present application further includes:
step S731: if the first quantity information is larger than 1, judging whether the error actions are the same;
step S732: if the error actions are the same, third reminding information is obtained, and the third reminding information is used for reminding a plurality of people of the same error in the first frame;
step S733: if the error actions are different, obtaining the type information of each error action;
step S734: and obtaining fourth reminding information according to the type information, wherein the fourth reminding information is used for reminding a plurality of people of the multi-type errors in the first frame.
Specifically, when the first quantity information is not 0, and whether the first quantity information is greater than 1 is determined, if the first quantity information is greater than 1, a plurality of people in the first frame have a malfunction. Judging whether the error actions are the same; if the first frame is the same as the second frame, sending a third reminding message to remind a plurality of people of the same error in the first frame. And if the error actions are different, obtaining the type information of each error action based on the error actions, and sending fourth reminding information to remind a plurality of people of the occurrence of the multi-type errors in the first frame. For example, if the first amount information is 5, it indicates that 5 people have a malfunction in the first frame, and the condition that the first amount information is greater than 1 is met. Further, whether the error actions of the 5 persons are the same or not is judged; if the 5 persons have the same error action, sending a third reminding message; if the 5 persons have different false actions, identifying the type information of each false action and sending out a fourth reminding message. When the same error and multiple types of errors occur in the first frame, a plurality of personnel send out a prompt; and then the auxiliary teacher carries out the gymnastics teaching, promotes the technical effect of gymnastics teaching quality.
Further, step S700 of the present application further includes:
step S750: obtaining a first predetermined time threshold;
step S760: obtaining second quantity information of the false actions in the first video information within the first preset time threshold;
step S770: obtaining a predetermined number threshold;
step S780: determining whether the second amount of information for the false action is within the predetermined amount threshold;
step S790: and if the second quantity information of the error actions exceeds the preset quantity threshold value, acquiring the node information of the error actions.
Specifically, the video within a period of time in the first evaluation result is analyzed to obtain a first predetermined time threshold, and the first predetermined time threshold can be set adaptively. And obtaining second quantity information of the error actions within the first preset time threshold according to the first video information. The second quantity information represents the number of persons with a malfunction within the first predetermined time threshold. Further, comparing the second quantity information of the false actions with the predetermined quantity threshold; and if the second quantity information of the error actions exceeds the preset quantity threshold value, acquiring the node information of the error actions. The preset number threshold is the preset number of people with misoperation, and when the preset number threshold is exceeded, the number of people with misoperation is large, so that high attention of teachers is required. And the node information of the error action is beat information corresponding to the error action. For example, the first predetermined time threshold is defined to be 1 minute and the predetermined number threshold is defined to be 4. Analyzing any 1 minute in the first video information to obtain 6 second quantity information of the error action. And comparing the second quantity information of the error actions with the preset quantity threshold value to obtain that the second quantity information of the error actions exceeds the preset quantity threshold value, and obtaining the node information corresponding to the error actions based on the second quantity information of the error actions. The technical effects of obtaining the node information of the error action and laying a foundation for the fifth reminding information are achieved.
Further, step S790 of the present application further includes:
step S7100: judging whether the interval beat length between the generation node information exceeds a preset interval beat length or not;
step S7110: if the interval beat length between the generation node information does not exceed the preset interval beat length, determining an exercise beat;
step S7120: according to the error action, acquiring personnel information corresponding to the error action;
step S7130: and acquiring fifth reminding information according to the personnel information and the exercise tempo, wherein the fifth reminding information is used for reminding the personnel to exercise the exercise tempo.
Specifically, after the generation node information of the false action is obtained, the interval beat length between the generation node information of the false action is compared with the predetermined interval beat length; and if the interval beat length between the generation node information does not exceed the preset interval beat length, the error actions are more intensive and are concentrated in one preset interval beat length. And determining the beat corresponding to the interval beat length between the generation node information. The length of the beat of the preset interval is a preset standard for judging whether the error actions of the node information of the error actions are dense or not. Further, identifying personnel information corresponding to the error action according to the error action; and reminding the person to practice the practice tempo through the fifth reminding information. The fifth reminding information comprises personnel information corresponding to the misoperation and beat information used for practicing by the personnel information. The technical effect of reminding the corresponding personnel of the wrong action to carry out the exercise of the corresponding beat when the wrong action is dense is achieved.
Further, step S7100 of the present application further includes:
step S7101: if the interval beat length between the generation node information exceeds the preset interval beat length, paragraph division is carried out according to the interval beat length between the generation node information to obtain a plurality of exercise paragraphs;
step S7102: and performing segmented exercise according to the plurality of exercise segments.
Specifically, if the interval beat length between the generation node information exceeds the predetermined interval beat length, it indicates that the false actions are not intensive. For example, at the first eight beats, a first false action occurs; at the fourth eighth beat, a second malfunction occurs. According to the interval beat length between the generation node information, paragraph division is carried out to obtain a plurality of exercise paragraphs; and performing segmentation exercise. For example, each eight-beat of the gymnastics is divided into a paragraph, and each eight-beat is respectively exercised. The technical effects of performing paragraph division and sectional exercise on the exercise motions when the error motions are not intensive are achieved.
Further, step S500 of the present application further includes:
step S510: acquiring actual beat information corresponding to each action of a first person in the first action set;
step S520: comparing the actual beat information with the standard beat information, and judging whether the actual beat information is the same as the standard beat information;
step S530: and if the actual tempo information is different from the standard tempo information, acquiring sixth reminding information, wherein the sixth reminding information is used for reminding the first person of rhythm errors.
Specifically, actual beat information corresponding to each motion of the first person is obtained from the first motion set. The actual tempo information corresponding to each action of the first person is the actual tempo information corresponding to each action of any one person in the first action set. And comparing the actual beat information with the standard beat information, judging whether the actual beat information and the standard beat information are the same, and if not, sending sixth reminding information to remind the first person of rhythm errors. The technical effect of reminding the rhythm errors is achieved.
In summary, the exercise assistant teaching method provided by the application has the following technical effects:
1. acquiring first video information through a video acquisition device; obtaining standard motions of a first body-building exercise and standard beat information matched with the standard motions; further, training the neural network model, and constructing a gymnastics action evaluation model; performing traversal feature extraction on the action of each person in each frame in the first video information to obtain a first action set; further, beat information corresponding to each piece of action information in the first action set is obtained; inputting each action information in the first action set and beat information corresponding to each action information into the fitness operation evaluation model to obtain a first evaluation result; and analyzing the first reminding information to obtain first reminding information and assist teachers to perform gymnastics teaching. Timely and efficient reminding of the error actions of the gymnastics is achieved; the teaching effect of the gymnastics is improved; optimizing a teaching method of the gymnastics; improving the teaching and evaluation system of the gymnastics; meanwhile, an intelligent fitness operation evaluation model is designed to assist teachers in fitness exercise teaching, so that the energy and physical strength of the teachers are saved; help students to master the knowledge and skill of gymnastics; the technical effect of deepening the understanding of students on the essential characteristics of the gymnastics is achieved.
2. The existing video monitoring system has the limitations and disadvantages of short transmission distance, easy distortion of video, poor system expansibility, difficult integration between systems and the like. Preferably, the video acquisition device is adopted to acquire the gymnastics and sports video information of the user.
3. The teaching evaluation is to carry out quantitative and qualitative value judgment on the teaching quality according to the teaching target and the value scale. The assessment of the aerobics exercises is mainly performed by technical evaluation, the standard actions in the eyes of the referees are high-quality actions, and different referees give different scores for the same set of actions of the same person. The action evaluation system of aerobics exercises needs to be improved and perfected. Preferably, the exercise operation evaluation model is adopted to objectively evaluate exercise operation information of the user and beat information corresponding to each action information. The body-building operation evaluation model is a neural network model obtained by training the neural network model through the standard operation and the standard beat information, and has the characteristics of the neural network model. The neural network model is a neural network model in machine learning, reflects many basic characteristics of human brain functions, is a deep feedforward neural network with the characteristics of local connection, weight sharing and the like, and is a highly complex nonlinear dynamic learning system.
Example two
Based on the same inventive concept as the teaching method for assisting exercise in the aforementioned embodiment, the present invention further provides a teaching system for assisting exercise, where the system includes a video capture device, please refer to fig. 4, and the system further includes:
the first obtaining unit 11 is configured to obtain first video information through the video acquisition device, where the first video information includes video information of multiple persons performing exercises;
a second obtaining unit 12, wherein the second obtaining unit 12 is used for obtaining a standard motion of the first gymnastics and standard beat information matched with the standard motion;
the first execution unit 13 is configured to train a neural network model according to the standard motion and the standard beat information, and construct a gymnastics motion evaluation model;
a third obtaining unit 14, where the third obtaining unit 14 is configured to perform traversal feature extraction on an action of each person in each frame of the video according to the first video information, and obtain a first action set, where the first action set includes action information of each person in each frame;
a fourth obtaining unit 15, where the fourth obtaining unit 15 is configured to obtain, according to the standard beat information, beat information corresponding to each piece of action information in the first action set;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to input each piece of motion information in the first motion set and beat information corresponding to each piece of motion information into the exercise operation evaluation model to obtain a first evaluation result, where the first evaluation result includes wrong motion information and wrong beat information in the first video information;
a sixth obtaining unit 17, where the sixth obtaining unit 17 is configured to analyze the first evaluation result to obtain first prompting information, and the first prompting information is used to assist a teacher in performing gymnastics teaching.
Further, the system further comprises:
a seventh obtaining unit, configured to obtain information of a first number of false actions in a first frame according to the first evaluation result;
a first judging unit configured to judge whether the first quantity information is 0;
a second determination unit configured to determine whether the first number information is greater than 1 if the first number information is not 0;
an eighth obtaining unit, configured to obtain second reminding information if the first quantity information is equal to 1, where the second reminding information is used to remind a person of an error occurring in the first frame.
Further, the system further comprises:
a third judging unit, configured to judge whether the error actions are the same or not if the first quantity information is greater than 1;
a ninth obtaining unit, configured to obtain third reminding information if the error actions are the same, where the third reminding information is used to remind a plurality of people of the same error occurring in the first frame;
a tenth obtaining unit configured to obtain type information of each of the erroneous actions if the erroneous actions are different;
an eleventh obtaining unit, configured to obtain fourth reminding information according to the type information, where the fourth reminding information is used to remind a plurality of people of a multi-type error in the first frame.
Further, the system further comprises:
a twelfth obtaining unit configured to obtain a first predetermined time threshold;
a thirteenth obtaining unit, configured to obtain second quantity information of the false actions in the first video information within the first predetermined time threshold;
a fourteenth obtaining unit for obtaining a predetermined number of thresholds;
a fourth judging unit configured to judge whether or not the second number information of the erroneous operation is within the predetermined number threshold;
a fifteenth obtaining unit configured to obtain occurrence node information of the false action if the second quantity information of the false action exceeds the predetermined quantity threshold.
Further, the system further comprises:
a fifth judging unit, configured to judge whether an interval beat length between the generation node information exceeds a predetermined interval beat length;
a first execution unit configured to determine a practice tempo if an interval tempo length between the generation node information does not exceed the predetermined interval tempo length;
a sixteenth obtaining unit, configured to obtain, according to the error action, staff information corresponding to the error action;
a seventeenth obtaining unit, configured to obtain fifth prompting information according to the staff information and the exercise tempo, where the fifth prompting information is used to prompt the staff to perform exercise of the exercise tempo.
Further, the system further comprises:
an eighteenth obtaining unit, configured to, if the interval beat length between the occurrence node information exceeds the predetermined interval beat length, perform paragraph division according to the interval beat length between the occurrence node information, and obtain a plurality of exercise paragraphs;
a second execution unit configured to perform a segmentation exercise according to the plurality of exercise segments.
Further, the system further comprises:
a nineteenth obtaining unit, configured to obtain actual beat information corresponding to each action of the first person in the first action set;
a sixth judging unit, configured to compare the actual beat information with the standard beat information, and judge whether the actual beat information is the same as the standard beat information;
a twentieth obtaining unit, configured to obtain sixth prompting information if the actual tempo information is different from the standard tempo information, where the sixth prompting information is used to prompt the first person that a tempo error occurs.
The embodiments in the present description are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the aforementioned exercise assisting teaching method and specific example in the first embodiment of fig. 1 are also applicable to an exercise assisting teaching system in this embodiment, and through the foregoing detailed description of an exercise assisting teaching method, a person skilled in the art can clearly know an exercise assisting teaching system in this embodiment, so for the brevity of the description, detailed descriptions are omitted here. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Exemplary electronic device
The computer apparatus of the present application is described below with reference to fig. 5. The computer device may be an application version management server or a terminal, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of processing an application package.
When the computer device is a terminal, the computer device may further comprise a display screen and an input means. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer-readable storage medium. The computer instructions are read by a processor of the computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the steps of the above-described method embodiments.
The application provides a gymnastics auxiliary teaching method, wherein the method is applied to a gymnastics auxiliary teaching system, the system comprises a video acquisition device, and the method comprises the following steps: acquiring first video information through a video acquisition device; obtaining standard motions of a first body-building exercise and standard beat information matched with the standard motions; further, training the neural network model, and constructing a gymnastics action evaluation model; performing traversal feature extraction on the action of each person in each frame in the first video information to obtain a first action set; further, beat information corresponding to each piece of action information in the first action set is obtained; inputting each action information in the first action set and beat information corresponding to each action information into the fitness operation evaluation model to obtain a first evaluation result; and analyzing the first reminding information to obtain first reminding information to assist a teacher in performing gymnastics teaching. The technical problem of the prior art that the teaching effect of the gymnastics is poor due to the lack of timely and efficient reminding of the wrong actions of the gymnastics is solved. Timely and efficient reminding of the error actions of the gymnastics is achieved; the teaching effect of the gymnastics is improved; optimizing a teaching method of the gymnastics; improving the teaching and evaluation system of the gymnastics; meanwhile, an intelligent fitness operation evaluation model is designed to assist teachers in fitness exercise teaching, so that the energy and physical strength of the teachers are saved; help students to master the knowledge and skill of gymnastics; the technical effect of deepening the understanding of students on the essential characteristics of the gymnastics is achieved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (9)
1. A gymnastics auxiliary teaching method is applied to a gymnastics auxiliary teaching system, the system comprises a video acquisition device, and the method comprises the following steps:
acquiring first video information through the video acquisition device, wherein the first video information comprises video information of a plurality of persons performing gymnastics;
obtaining a standard action of a first body-building exercise and standard beat information matched with the standard action;
training a neural network model according to the standard motion and the standard beat information, and constructing a gymnastics motion evaluation model;
performing traversal feature extraction on the action of each person in each frame of the video according to the first video information to obtain a first action set, wherein the first action set comprises the action information of each person in each frame;
obtaining beat information corresponding to each piece of action information in the first action set according to the standard beat information;
inputting each action information in the first action set and beat information corresponding to each action information into the exercise action evaluation model to obtain a first evaluation result, wherein the first evaluation result comprises wrong action information and wrong beat information in the first video information;
analyzing the first evaluation result to obtain first reminding information, wherein the first reminding information is used for assisting a teacher in performing gymnastics teaching;
after obtaining the standard motion of the first gymnastics and the standard beat information matched with the standard motion, the method comprises the following steps:
acquiring actual beat information corresponding to each action of a first person in the first action set;
comparing the actual beat information with the standard beat information, and judging whether the actual beat information is the same as the standard beat information;
and if the actual tempo information is different from the standard tempo information, acquiring sixth reminding information, wherein the sixth reminding information is used for reminding the first person of rhythm errors.
2. The method of claim 1, wherein analyzing the first evaluation result to obtain a first reminder information, the first reminder information being used to assist a teacher in performing gym teaching, comprises:
obtaining first quantity information of the error actions in the first frame according to the first evaluation result;
judging whether the first quantity information is 0 or not;
if the first quantity information is not 0, judging whether the first quantity information is larger than 1;
and if the first quantity information is equal to 1, obtaining second reminding information, wherein the second reminding information is used for reminding a person of errors in the first frame.
3. The method of claim 2, wherein after determining whether the first amount of information is greater than 1 if the first amount of information is not 0, further comprising:
if the first quantity information is larger than 1, judging whether the error actions are the same;
if the error actions are the same, third reminding information is obtained, and the third reminding information is used for reminding a plurality of people of the same error in the first frame;
if the error actions are different, obtaining the type information of each error action;
and obtaining fourth reminding information according to the type information, wherein the fourth reminding information is used for reminding a plurality of people of multi-type errors in the first frame.
4. The method of claim 1, wherein the method further comprises:
obtaining a first predetermined time threshold;
obtaining second quantity information of the false actions in the first video information within the first preset time threshold;
obtaining a predetermined number threshold;
determining whether the second amount of information for the false action is within the predetermined amount threshold;
and if the second quantity information of the error actions exceeds the preset quantity threshold value, acquiring the node information of the error actions.
5. The method of claim 4, wherein after obtaining the node information of occurrence of the false action if the second amount information of the false action exceeds the predetermined number threshold, further comprising:
judging whether the interval beat length between the generation node information exceeds a preset interval beat length or not;
if the interval beat length between the generation node information does not exceed the preset interval beat length, determining an exercise beat;
according to the error action, acquiring personnel information corresponding to the error action;
and acquiring fifth reminding information according to the personnel information and the exercise tempo, wherein the fifth reminding information is used for reminding the personnel to exercise the exercise tempo.
6. The method of claim 5, wherein after determining whether the interval beat length between the generation node information exceeds a predetermined interval beat length, further comprising:
if the interval beat length between the generation node information exceeds the preset interval beat length, paragraph division is carried out according to the interval beat length between the generation node information to obtain a plurality of exercise paragraphs;
and performing segmented exercise according to the plurality of exercise segments.
7. The utility model provides a gymnastics auxiliary teaching system, the system includes video acquisition device, its characterized in that, the system still includes:
the first obtaining unit is used for obtaining first video information through the video collecting device, and the first video information comprises video information of a plurality of persons performing gymnastics;
the second obtaining unit is used for obtaining a standard action of the first body-building exercise and standard beat information matched with the standard action;
the first execution unit is used for training a neural network model according to the standard action and the standard beat information to construct a gymnastics action evaluation model;
a third obtaining unit, configured to perform traversal feature extraction on an action of each person in each frame of the video according to the first video information, and obtain a first action set, where the first action set includes action information of each person in each frame;
a fourth obtaining unit, configured to obtain, according to the standard beat information, beat information corresponding to each piece of action information in the first action set;
a fifth obtaining unit, configured to input each piece of motion information in the first motion set and beat information corresponding to each piece of motion information into the exercise operation evaluation model to obtain a first evaluation result, where the first evaluation result includes wrong motion information and wrong beat information in the first video information;
a sixth obtaining unit, configured to analyze the first evaluation result to obtain first prompting information, where the first prompting information is used to assist a teacher in performing gymnastics teaching;
a nineteenth obtaining unit, configured to obtain actual beat information corresponding to each action of the first person in the first action set;
a sixth judging unit, configured to compare the actual beat information with the standard beat information, and judge whether the actual beat information is the same as the standard beat information;
a twentieth obtaining unit, configured to obtain sixth prompting information if the actual tempo information is different from the standard tempo information, where the sixth prompting information is used to prompt the first person that a tempo error occurs.
8. An exercise assisted instruction system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any of claims 1 to 6 are carried out by the processor when the program is executed.
9. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210806144.0A CN115205740B (en) | 2022-07-08 | 2022-07-08 | Body-building exercise auxiliary teaching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210806144.0A CN115205740B (en) | 2022-07-08 | 2022-07-08 | Body-building exercise auxiliary teaching method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115205740A CN115205740A (en) | 2022-10-18 |
| CN115205740B true CN115205740B (en) | 2023-03-24 |
Family
ID=83579721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210806144.0A Active CN115205740B (en) | 2022-07-08 | 2022-07-08 | Body-building exercise auxiliary teaching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115205740B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109618060A (en) * | 2019-01-13 | 2019-04-12 | 王榕 | A kind of healthalert alarm clock method, terminal |
| CN113539419A (en) * | 2021-08-01 | 2021-10-22 | 重庆医科大学附属第一医院 | Method and system for evaluating stroke gymnastics effect |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108805068A (en) * | 2018-06-01 | 2018-11-13 | 李泽善 | A kind of motion assistant system, method, apparatus and medium based on student movement |
| CN110738192A (en) * | 2019-10-29 | 2020-01-31 | 腾讯科技（深圳）有限公司 | Human motion function auxiliary evaluation method, device, equipment, system and medium |
| CN113128283A (en) * | 2019-12-31 | 2021-07-16 | 沸腾时刻智能科技(深圳)有限公司 | Evaluation method, model construction method, teaching machine, teaching system and electronic equipment |
| US11539985B2 (en) * | 2020-12-16 | 2022-12-27 | Istreamplanet Co., Llc | No reference realtime video quality assessment |
| CN114022512A (en) * | 2021-10-30 | 2022-02-08 | 平安国际智慧城市科技股份有限公司 | Exercise assisting method, apparatus and medium |
| CN114495177A (en) * | 2022-04-06 | 2022-05-13 | 北京蓝田医疗设备有限公司 | Scene interactive human body action and balance intelligent evaluation method and system |
-
2022
- 2022-07-08 CN CN202210806144.0A patent/CN115205740B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109618060A (en) * | 2019-01-13 | 2019-04-12 | 王榕 | A kind of healthalert alarm clock method, terminal |
| CN113539419A (en) * | 2021-08-01 | 2021-10-22 | 重庆医科大学附属第一医院 | Method and system for evaluating stroke gymnastics effect |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115205740A (en) | 2022-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460305B (en) | Method for assisting bicycle training, readable storage medium and electronic device | |
| CN108734104B (en) | Body-building action error correction method and system based on deep learning image recognition | |
| Velloso et al. | Qualitative activity recognition of weight lifting exercises | |
| JP2016524929A (en) | Analysis of portable computing devices and personal data captured from them | |
| CN105451828A (en) | Report system for physiotherapeutic and rehabilitative video games | |
| Novatchkov et al. | Machine learning methods for the automatic evaluation of exercises on sensor-equipped weight training machines | |
| Osgouei et al. | Rehabilitation exergames: Use of motion sensing and machine learning to quantify exercise performance in healthy volunteers | |
| Williams et al. | Assessment of physical rehabilitation movements through dimensionality reduction and statistical modeling | |
| Liu et al. | Trampoline motion decomposition method based on deep learning image recognition | |
| JP2005111178A (en) | Motion training display system | |
| CN112966370B (en) | Design method of human body lower limb muscle training system based on Kinect | |
| CN115205740B (en) | Body-building exercise auxiliary teaching method and system | |
| Tsiakas et al. | Towards designing a socially assistive robot for adaptive and personalized cognitive training | |
| Mahendran | Deep learning for fitness | |
| Rozaliev et al. | Methods and applications for controlling the correctness of physical exercises performance | |
| Huang | The influence of Sports Dance on the physical and Mental Development of Contemporary College Students based on Health detection | |
| CN115985462A (en) | Rehabilitation and intelligence-developing training system for children cerebral palsy | |
| Cao et al. | Football players’ strength training method using image processing based on machine learning | |
| Wang et al. | The Application of Computer-Based Virtual Technology in Volleyball Training | |
| CN114642424A (en) | Physical ability assessment method and device based on somatosensory interaction technology | |
| Talaat | Novel deep learning models for yoga pose estimator | |
| Hong | Kinect and Few-Shot Technology-Based Simulation of Physical Fitness and Health Training Model for Basketball Players in Plateau Area | |
| Zhao et al. | Research on the identification and evaluation of aerobics movements based on deep learning | |
| Gao | Construction and simulation of athlete’s wrong action recognition model in sports training based on embedded wireless communication and computer vision | |
| Sun | Aerobics movement decomposition action teaching system based on intelligent vision sensor |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |