Dance motion teaching system and method based on motion perception

Abstract

The invention discloses a dance movement teaching system and method based on movement perception, and belongs to the technical field of dance teaching. Physiological data of students during dance training are collected, and the dance difficulty is evaluated according to a dance difficulty evaluation strategy; collecting exercise data of the student after the training unit is completed, and evaluating the tidiness of the student during training according to a dance tidiness evaluation strategy; images of the students during dance training are collected in real time, and standard dance conditions of the students during training are evaluated according to the dance posture evaluation model; evaluating a dance teaching comprehensive condition based on the dance difficulty, the dance uniformity and the dance accuracy; judging whether the dance teacher needs to teach again or not based on the comprehensive dance teaching condition; the training data is collected, the dance difficulty, the dance uniformity and the dance accuracy are combined to analyze the teaching condition, the teaching condition can be mastered more accurately, the wrong posture can be corrected in time, and the dance teaching quality and efficiency can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of dance teaching, and particularly relates to a dance movement teaching system and method based on motion perception. Background Art

[0002] Dance is a performing art that uses the body to complete various elegant or difficult movements. The current dance teaching method is that the dance teacher explains dance knowledge and demonstrates dance movements, and the students train after observing the teacher's demonstration movements. Due to the differences in the physical conditions of each student, the learning quality is also different. The dance teacher needs to judge whether repeated teaching is required based on teaching experience, and the teaching quality depends more on the teacher's teaching experience. In this case, it is extremely necessary to automatically evaluate the teaching quality based on the dance postures of the students;

[0003] Most of the existing technologies for evaluating dance postures judge by measuring the matching degree between human movements and template movements, lacking the division of dances into training units and the joint analysis of dance teaching quality in combination with dance complexity, dance neatness, and dance accuracy, thus being unable to accurately evaluate the completion of each training unit and the dance postures at any time frame of the students, resulting in low teaching efficiency;

[0004] To solve the above problems, the present invention designs a dance movement teaching system and method based on motion perception. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the present invention designs a dance movement teaching system and method based on motion perception. The present invention collects the physiological data of students during dance training and evaluates the dance difficulty according to the dance difficulty evaluation strategy; collects the motion data of students when a training unit is completed and evaluates the neatness of the students during training according to the dance neatness evaluation strategy; collects the images of students during dance training in real time and evaluates the standard situation of the dance of the students during training according to the dance posture evaluation model; evaluates the comprehensive situation of dance teaching based on the dance difficulty, dance neatness, and dance accuracy; judges whether the dance teacher needs to reteach based on the comprehensive dance teaching situation; the present invention collects training data, combines the dance difficulty, dance neatness, and dance accuracy to analyze the teaching situation, can more accurately grasp the teaching situation, correct incorrect postures in time, and is beneficial to improving the quality and efficiency of dance teaching.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A dance movement teaching method based on motion perception, comprising the following specific steps:

[0008] S1. Collect the physiological data of students during dance training and evaluate the dance difficulty according to the dance difficulty evaluation strategy;

[0009] S2. Collect the motion data of students when the training unit is completed, and evaluate the neatness of students' training according to the dance neatness evaluation strategy;

[0010] S3. Collect the images of students during dance training in real time, and evaluate the standard situation of students' dance during training according to the dance posture evaluation model;

[0011] S4. Evaluate the comprehensive situation of dance teaching based on the dance difficulty, dance neatness and dance accuracy;

[0012] S5. Judge whether the dance teacher needs to re-teach based on the comprehensive dance teaching situation.

[0013] Specifically, S1 includes the following specific steps:

[0014] S11. Collect the physiological data of students during dance training, and the physiological data includes heart rate, respiratory rate and energy consumption;

[0015] S12. Import the heart rate, respiratory rate and energy consumption into the dance complexity value calculation formula to calculate the dance complexity value. The dance complexity value calculation formula is:

[0016]

[0017] In the formula, λ 1 is the heart rate proportion coefficient, λ 2 is the respiratory rate proportion coefficient, λ 3 is the energy consumption proportion coefficient, λ 1 > 0, λ 2 > 0, λ 3 > 0 and λ 1 + λ 2 + λ 3 = 1, H ij is the heart rate of the i-th student in the j-th time period, H bz is the standard heart rate in the unit time period, B ij is the respiratory rate of the i-th student in the j-th time period, B bz is the standard respiratory rate in the unit time period, X ij is the energy consumption of the i-th student in the j-th time period, X bz is the standard energy consumption in the unit time period, I is the total number of students collected, and J is the total number of time periods collected.

[0018] Specifically, S2 includes the following specific steps:

[0019] S21. Divide the training dance into several training units, collect the motion data of students when the training unit is completed, and the motion data includes coordinates and completion time, and the coordinates include the head coordinates, hand coordinates and foot coordinates of the students;

[0020] S22. Import the head coordinates, hand coordinates, and foot coordinates of a single student in the set training unit into the action offset value calculation formula to calculate the action offset value of the student. The action offset value calculation formula is as follows:

[0021]

[0022] In the formula, θ h is the angle of the h-th part of the student, is the standard angle of the h-th part;

[0023] S23. Import the action offset value and the completion time into the dance uniformity calculation formula to calculate the dance uniformity. The dance uniformity calculation formula is as follows:

[0024]

[0025] In the formula, α 1 is the action offset proportion coefficient, α 2 is the completion time proportion coefficient, α 1 > 0, α 2 > 0 and α 1 + α 2 = 1, is the action offset value of the i-th student in the n-th training unit, N is the total number of training units, is the average action offset value of the n-th training unit, T in is the completion time of the i-th student in the n-th training unit, is the standard completion time of the n-th training unit.

[0026] Specifically, the S3 includes the following specific steps:

[0027] S31. Real-time collect the images of students during dance training and extract key points through the images;

[0028] S32. Import the key points into the dance posture standard value calculation formula to calculate the standard value of the dance during students' training. The dance posture standard value calculation formula is as follows:

[0029]

[0030] In the formula, S is the standard posture sequence, S = {S 1 , S 2 ,..., S p}, where S p is the posture feature of the standard posture sequence at time frame p, that is, S p = ((x 1 , y 1 ), (x2 , y 2 ),...,(x k , y k )),Z is the posture sequence to be measured, Z = {Z 1 , Z 2 ,..., Z p}, where Z p is the posture feature of the posture sequence to be measured at time frame p, that is, Z p = ((x 11 , y 11 ), (x 12 , y 12 ),...,(x 1k , y 1k )),DTW(S, Z) is the DTW distance between sequences S and T, DTW′ is the standard DTW distance, ΔS pm is the displacement vector of the m-th key point at the p-th time frame in the standard action sequence, ΔZ pm is the displacement vector of the m-th key point at the p-th time frame in the action sequence to be measured, ||*|| 2 is the Euclidean distance, P is the total number of time frames, M is the total number of key points in the posture feature of a single time frame, L′ is the standard distance of key points, and exp(*) is the exponential function with the real number e as the base.

[0031] Specifically, S4 includes the following specific steps:

[0032] Import the dance complexity value, dance neatness value, and dance posture standard value into the dance teaching comprehensive evaluation value calculation formula to calculate the dance teaching comprehensive evaluation value. The dance teaching comprehensive evaluation value calculation formula is:

[0033]

[0034] In the formula, β 1 is the proportion coefficient of the dance complexity value, β 2 is the proportion coefficient of the dance neatness value, β 3 is the proportion coefficient of the dance posture standard value, β 1 > 0, β 2 > 0, β 3 > 0 and β 1 + β 2 + β 3 = 1, is the dance posture standard value of the i-th student.

[0035] Specifically, S5 includes the following specific steps:

[0036] Compare the comprehensive dance teaching evaluation value with the preset comprehensive dance teaching threshold. If the comprehensive dance teaching evaluation value is less than the preset comprehensive dance teaching threshold, it is determined that the dance student can study independently; if the comprehensive dance teaching evaluation value is greater than or equal to the preset comprehensive dance teaching threshold, it is determined that the dance requires the dance teacher to teach again.

[0037] A dance movement teaching system based on motion perception is used to implement a dance movement teaching method based on motion perception, including a control module, a data acquisition module, a difficulty evaluation module, a neatness evaluation module, an image processing module, a posture evaluation module, a comprehensive teaching evaluation module, and a comparison and judgment module;

[0038] Specifically, the control module is used to control the operation of the data acquisition module, the difficulty evaluation module, the neatness evaluation module, the image processing module, the posture evaluation module, the comprehensive teaching evaluation module, and the comparison and judgment module;

[0039] The data acquisition module is used to collect the physiological data of students during dance training and the motion data of students when completing training units;

[0040] The difficulty evaluation module is used to import the heart rate, respiratory rate, and energy consumption into the dance complexity value calculation formula to calculate the dance complexity value;

[0041] The neatness evaluation module is used to first import the coordinates into the action offset value calculation formula to calculate the action offset value of the student, and then import the action offset value and the completion time into the dance neatness calculation formula to calculate the dance neatness;

[0042] The image processing module is used to collect the images of students during dance training in real time and perform image preprocessing to extract key points;

[0043] The posture evaluation module is used to import the key points into the dance posture standard value calculation formula to calculate the standard value of the dance during the student's training;

[0044] The comprehensive teaching evaluation module is used to import the dance complexity value, the dance neatness, and the dance posture standard value into the dance teaching comprehensive evaluation value calculation formula to calculate the dance teaching comprehensive evaluation value;

[0045] The comparison and judgment module is used to compare the dance teaching comprehensive evaluation value with the preset comprehensive dance teaching threshold, and determine whether the dance teacher needs to teach again according to the comparison result.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] The present invention collects the physiological data of students during dance training and evaluates the dance difficulty according to the dance difficulty evaluation strategy; collects the motion data of students when a training unit is completed and evaluates the neatness of students during training according to the dance neatness evaluation strategy; collects the images of students during dance training in real time and evaluates the standardness of the dance of students during training according to the dance posture evaluation model; evaluates the comprehensive dance teaching situation based on the dance difficulty, dance neatness and dance accuracy; determines whether the dance teacher needs to reteach based on the comprehensive dance teaching situation. The present invention collects training data, combines and analyzes the dance difficulty, dance neatness and dance accuracy to evaluate the teaching situation, can more accurately grasp the teaching situation, correct incorrect postures in time, and is beneficial to improving the quality and efficiency of dance teaching. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0049] Figure 1 It is a schematic flow chart of the dance movement teaching method based on motion perception of the present invention;

[0050] Figure 2 It is a schematic diagram of coordinate system construction in the dance teaching posture evaluation method of the present invention;

[0051] Figure 3 It is a schematic diagram of the overall framework of the dance movement teaching system based on motion perception of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] Now, the exemplary embodiments will be described more comprehensively with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present invention will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The features, structures or characteristics described can be combined in any suitable manner in one or more embodiments.

[0053] Embodiment 1

[0054] Please refer to Figure 1 , an embodiment provided by the present invention:

[0055] A dance movement teaching method based on motion perception, which includes the following specific steps:

[0056] S1. Collect the physiological data of students during dance training and evaluate the dance difficulty according to the dance difficulty evaluation strategy;

[0057] In this embodiment, S1 includes the following specific steps:

[0058] S11. Collect the physiological data of students during dance training. The physiological data includes heart rate, respiratory rate, and energy consumption;

[0059] It should be noted in this embodiment that the heart rate, respiratory rate, and energy consumption are monitored by wearable devices; wear a heart rate monitor belt. Before the student starts dancing, turn on the device to start recording heart rate data, and record heart rate data in real time during the dancing process; wear an acceleration sensor. The acceleration sensor monitors the chest movement caused by breathing, and records the number of rises and falls to calculate the respiratory rate; input information such as the student's age, weight, height, and gender in advance to calculate energy consumption more accurately during the dancing process; when the student starts dancing, record the start time point. During the dancing process, continuously record the data of heart rate, respiratory rate, and energy consumption. When the student finishes dancing, record the end time point.

[0060] S12. Import the heart rate, respiratory rate, and energy consumption into the dance complexity value calculation formula to calculate the dance complexity value. The dance complexity value calculation formula is:

[0061]

[0062] In the formula, λ 1 is the heart rate proportion coefficient, λ 2 is the respiratory rate proportion coefficient, λ 3 is the energy consumption proportion coefficient, λ 1 > 0, λ 2 > 0, λ 3 > 0 and λ 1 + λ 2 + λ 3 = 1, H ij is the heart rate of the i-th student in the j-th time period, H bz is the standard heart rate in the unit time period, B ij is the respiratory rate of the i-th student in the j-th time period, B bz is the standard respiratory rate in the unit time period, X ij is the energy consumption of the i-th student in the j-th time period, X bz is the standard energy consumption in the unit time period, I is the total number of students collected, and J is the total number of time periods collected.

[0063] It should be noted that in this embodiment, the method for obtaining the standard heart rate within a unit time period is as follows: The average heart rate of adults in a quiet state is usually between 60 and 100 beats per minute. The maximum heart rate can be estimated by subtracting the age (for adults) from 220. The heart rate of dance students during intense dancing may reach 60% - 85% of the maximum heart rate. In this embodiment, the standard heart rate is taken as 68% of the maximum heart rate. For example, for a 20-year-old student, their heart rate may be between 120 and 170 beats per minute, and in this embodiment, the value is taken as 136 beats per minute;

[0064] The method for obtaining the standard breathing rate within a unit time period is as follows: The breathing rate of adults in a quiet state is usually between 12 and 20 times per minute. When dance students perform medium-intensity to high-intensity dances, the breathing rate may increase to 20 - 40 times per minute. In this embodiment, the standard breathing rate is taken as 30 times per minute;

[0065] The method for obtaining the standard energy consumption within a unit time period is as follows: The standard energy consumption in this embodiment is calculated by metabolic equivalent of task (METs). The MET value range for medium-intensity activities is 3.0 - 5.9, while the MET value for high-intensity activities reaches 6.0 or above. Generally, the MET value for medium-intensity dance is about 4.0, and for high-intensity dance is about 7.0. The calculation formula for the standard energy consumption is: Standard energy consumption (calories per minute) = MET value × body weight (kilograms) × 0.0175, where 0.0175 is the conversion coefficient for converting the MET value to calorie consumption. For example, when a student with a body weight of 60 kilograms performs medium-intensity dance (MET value of 4.0), their energy consumption per minute is approximately: 4.0 × 60 × 0.0175 = 4.05 calories per minute.

[0066] S2. Collect the motion data of students when the training unit is completed, and evaluate the neatness of students' training according to the dance neatness evaluation strategy;

[0067] In this embodiment, S2 includes the following specific steps:

[0068] S21. Divide the training dance into several training units, and collect the motion data of students when the training unit is completed. The motion data includes coordinates and completion time. The coordinates include the head coordinates, hand coordinates, and foot coordinates of the students;

[0069] It should be noted that in this embodiment, devices such as an optical motion capture system, an inertial measurement unit, and a depth camera are used. Students wear sensors on key parts such as the head, hands, and feet. When the students start dancing, the data acquisition system is started to record the time point when the students start the movement. The positions of the students' heads, hands, and feet are tracked in real time through the capture device, and the coordinate data and time stamps of each frame are recorded. After the movement is completed, the end time point is recorded, and the collected data is cleaned to remove noise and inaccurate measurement values;

[0070] Please refer to Figure 2 , the coordinate system construction method of this embodiment is as follows: taking the student's navel as the coordinate origin, drawing a line parallel to the ground through the coordinate origin as the X-axis, and drawing a line perpendicular to the ground through the coordinate origin as the Y-axis. Among them, the positions of the head coordinate positioning point, left hand coordinate positioning point, right hand coordinate positioning point, left foot coordinate positioning point, and right foot coordinate positioning point are as Figure 2 shown. Since the heights and weights of each student are different, the angle θ formed by each coordinate positioning point and the coordinate system is calculated to determine whether the movements are neat. For example, there are two vectors in a two-dimensional space and The calculation formula for the included angle θ is:

[0071]

[0072] In the formula, arccos is the inverse cosine in the inverse trigonometric function, · is the dot product between vectors, is the modulus of vector a, is the modulus of vector b,

[0073] S22. Import the head coordinates, hand coordinates, and foot coordinates of a single student in the set training unit into the action offset value calculation formula to calculate the action offset value of the student. The action offset value calculation formula is:

[0074]

[0075] In the formula, θ h is the angle of the hth part of the student, is the standard angle of the hth part;

[0076] It should be noted in this embodiment that the acquisition methods of the standard angles, including the standard head angle, standard left hand angle, standard right hand angle, standard left foot angle, and standard right foot angle, are as follows: Let the dance teacher wear sensors on key parts such as the head, hands, and feet, start the data acquisition system, record the coordinate data and timestamps of each frame of the dance teacher, obtain the completion time of each training unit of the dance teacher as the standard completion time, take the navel of the dance teacher as the coordinate origin, draw a line parallel to the ground through the coordinate origin as the X-axis, draw a line perpendicular to the ground through the coordinate origin as the Y-axis, obtain the head coordinate positioning point, left hand coordinate positioning point, right hand coordinate positioning point, left foot coordinate positioning point, and right foot coordinate positioning point of the dance teacher when each training unit is completed, calculate the angles formed by each coordinate positioning point and the coordinate system, and use the obtained angles as the standard head angle, standard left hand angle, standard right hand angle, standard left foot angle, and standard right foot angle of the training unit respectively.

[0077] S23. Import the action deviation value and completion time into the dance uniformity calculation formula to calculate the dance uniformity. The dance uniformity calculation formula is:

[0078]

[0079] In the formula, α 1 is the action deviation proportion coefficient, α 2 is the completion time proportion coefficient, α 1 >0, α 2 >0 and α 1 +α 2 =1, is the action deviation value of the i-th student in the n-th training unit, N is the total number of training units, is the average action deviation value of the n-th training unit, T in is the completion time of the i-th student in the n-th training unit, is the standard completion time of the n-th training unit.

[0080] S3. Real-time collect images of students during dance training, and evaluate the standard situation of the dance during students' training according to the dance posture evaluation model;

[0081] In this embodiment, S3 includes the following specific steps:

[0082] S31. Real-time collect images of students during dance training, and extract key points through the images;

[0083] In this embodiment, it should be noted that a high-definition camera is fixed, and students are arranged to conduct training within the effective capture range of the camera. The camera is connected to a computer, and video capture software is installed and configured. The image resolution and frame rate are set, and the path and format for saving images are configured. Before formal acquisition, the position and focal length of the camera are adjusted to ensure clear images. The collected image data needs to be preprocessed through image processing software, such as noise reduction, cropping, marking key points, etc.;

[0084] In this embodiment, OpenPose is used to estimate the human pose in the image. The OpenPose algorithm is a bottom-up human pose estimation algorithm, which mainly includes two key components: Part Affinity Fields (PAFs) and Confidence Maps;

[0085] Confidence Maps are used to detect the position of each key point in the image. For each key point, the algorithm generates a heatmap, and each pixel value in the heatmap represents the probability of the key point appearing at that position;

[0086] Part Affinity Fields (PAFs) are used to estimate the connection relationship between different key points, that is, limb parts. PAFs are a set of vector fields, and each vector field represents the connection direction and strength between two key points;

[0087] Input the images of students during dance training collected in real time, and input the images into a pre-trained neural network model. The model outputs a series of confidence maps and PAFs. Find the point with the highest probability in the confidence map as the position of the key point; use the PAFs information to determine the connection between key points, thereby forming a human skeleton, and store it in a structured data format, such as JSON, CSV, etc. Optimize the key point detection results through post-processing steps such as threshold filtering and non-maximum suppression. For example, filter out key points with poor detection effects according to the confidence level, and normalize the key point coordinates to the same scale for subsequent processing.

[0088] S32. Import the key points into the dance pose standard value calculation formula to calculate the standard value of the dance during students' training. The dance pose standard value calculation formula is:

[0089]

[0090] In the formula, S is the standard pose sequence, S = {S 1 , S 2 ,..., S p}, where S p is the pose feature of the standard pose sequence at time frame p, that is, S p = ((x1 , y 1 ), (x 2 , y 2 ),..., (x k , y k )), Z is the posture sequence to be measured, Z = {Z 1 , Z 2 ,..., Z p}, where Z p is the posture feature of the posture sequence to be measured in the time frame p, that is, Z p = ((x 11 , y 11 ), (x 12 , y 12 ),..., (x 1k , y 1k ))), DTW(S, Z) is the DTW distance between sequences S and T, DTW′ is the standard DTW distance, ΔS pm is the displacement vector of the m-th key point in the p-th time frame of the standard action sequence, ΔZ pm is the displacement vector of the m-th key point in the p-th time frame of the action sequence to be measured, ||*|| 2 is the Euclidean distance, P is the total number of time frames, M is the total number of key points in the posture feature of a single time frame, L′ is the standard distance of key points, and exp(*) is the exponential function with the real number e (e≈2.71828) as the base.

[0091] It should be noted in this embodiment that Dynamic Time Warping (abbreviated as DTW) is an algorithm for measuring the similarity between two time series. It calculates the optimal matching path between two sequences, allowing the time series to stretch and distort on the time axis, thereby effectively dealing with the matching problem of time series with different lengths and speeds. According to the DTW algorithm, the distance or similarity score between two time series is calculated. Usually, the lower the score, the more similar the two time series are;

[0092] Route evaluation can be calculated based on the displacement trajectory of key points. In this embodiment, the route is evaluated by calculating the displacement difference between two sequences at corresponding key points;

[0093] The Euclidean metric (also known as the Euclidean distance) is a commonly used distance definition, referring to the actual distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance from this point to the origin). The Euclidean distance in two-dimensional and three-dimensional spaces is the actual distance between two points;

[0094] The standard DTW distance DTW' and the standard key point distance L' are obtained as follows: Select 100 students with different genders, heights, ages, and weights and excellent dance scores. Input the real-time collected pictures of the students into the pre-trained neural network model to output the positions of the key points, forming 100 pose sequences. Calculate the DTW distance and the Euclidean distance between each of these 100 pose sequences and the standard pose sequence of the dance teacher, and take the average values as the standard DTW distance DTW' and the standard key point distance L' in this embodiment.

[0095] S4. Evaluate the comprehensive situation of dance teaching based on dance difficulty, dance uniformity, and dance accuracy;

[0096] In this embodiment, S4 includes the following specific steps:

[0097] Import the dance complexity value, dance uniformity, and dance pose standard value into the calculation formula of the comprehensive dance teaching evaluation value. The calculation formula of the comprehensive dance teaching evaluation value is:

[0098]

[0099] In the formula, β 1 is the proportion coefficient of the dance complexity value, β 2 is the proportion coefficient of the dance uniformity, β 3 is the proportion coefficient of the dance pose standard value, β 1 > 0, β 2 > 0, β 3 > 0 and β 1 + β 2 + β 3 = 1, is the dance pose standard value of the i-th student.

[0100] S5. Judge whether the dance teacher needs to reteach based on the comprehensive dance teaching situation.

[0101] In this embodiment, S5 includes the following specific steps:

[0102] Compare the comprehensive dance teaching evaluation value with the preset comprehensive dance teaching threshold. If the comprehensive dance teaching evaluation value is less than the preset comprehensive dance teaching threshold, it is judged that the dance student can study independently; if the comprehensive dance teaching evaluation value is greater than or equal to the preset comprehensive dance teaching threshold, it is judged that the dance needs to be taught again by the dance teacher.

[0103] It should be noted in this embodiment that the heart rate proportion coefficient λ 1 、the breathing rate proportion coefficient λ 2 、the energy consumption proportion coefficient λ 3 、the action deviation proportion coefficient α 1, Completion time proportion coefficient α 2 , Dance complexity value proportion coefficient β 1 , Dance neatness proportion coefficient β 2 , Dance posture standard value proportion coefficient β 3 The value-taking methods of the dance teaching comprehensive threshold are as follows: Select 500 students from a dance academy, collect the heart rate, breathing rate, and energy consumption of the students during dance training and import them into the dance complexity value calculation formula to calculate the dance complexity value; collect the coordinates and completion time and import them into the dance neatness calculation formula to calculate the dance neatness; collect the images of the students during dance training, obtain the key points and import them into the dance posture standard value calculation formula to calculate the standard value of the dance during the students' training. Import the dance complexity value, dance neatness, and dance posture standard value into the dance teaching comprehensive evaluation value calculation formula to calculate the dance teaching comprehensive evaluation value. The system determines whether the dance requires the dance teacher to teach again based on the dance teaching comprehensive evaluation value; Invite 50 dance experts to judge the dance situation of these 500 students and give the judgment result of whether the teacher needs to teach again. Import the judgment results of the system and the dance experts into the fitting software to output a set of heart rate proportion coefficients λ with the highest judgment similarity 1 , Breathing rate proportion coefficient λ 2 , Energy consumption proportion coefficient λ 3 , Action deviation proportion coefficient α 1 , Completion time proportion coefficient α 2 , Dance complexity value proportion coefficient β 1 , Dance neatness proportion coefficient β 2 , Dance posture standard value proportion coefficient β 3 and the value-taking of the dance teaching comprehensive threshold.

[0104] Embodiment 2

[0105] Please refer to Figure 3 , The dance movement teaching system based on action perception is used to implement the dance movement teaching method based on action perception, including a control module, a data acquisition module, a difficulty evaluation module, a neatness evaluation module, an image processing module, a posture evaluation module, a comprehensive teaching evaluation module, and a comparison and judgment module.

[0106] In this embodiment, the data acquisition module is used to collect the physiological data of the students during dance training and the movement data of the students when completing the training unit;

[0107] The difficulty evaluation module is used to import the heart rate, breathing rate, and energy consumption into the dance complexity value calculation formula to calculate the dance complexity value;

[0108] The neatness evaluation module is used to first import the coordinates into the action offset value calculation formula to calculate the action offset value of the student, and then import the action offset value and the completion time into the dance neatness calculation formula to calculate the dance neatness;

[0109] The image processing module is used to collect the images of students during dance training in real time, perform preprocessing on the images, and extract key points;

[0110] The posture evaluation module is used to import the key points into the dance posture standard value calculation formula to calculate the standard value of the dance during the student's training;

[0111] The comprehensive teaching evaluation module is used to import the dance complexity value, the dance neatness, and the dance posture standard value into the dance teaching comprehensive evaluation value calculation formula to calculate the dance teaching comprehensive evaluation value;

[0112] The comparison and judgment module is used to compare the dance teaching comprehensive evaluation value with the preset dance teaching comprehensive threshold, and judge whether the dance teacher needs to teach again according to the comparison result.

[0113] In this embodiment, the control module is used to control the operation of the data acquisition module, the difficulty evaluation module, the neatness evaluation module, the image processing module, the posture evaluation module, the comprehensive teaching evaluation module, and the comparison and judgment module.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, they generate the processes or functions according to the embodiments of the present invention in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or a data center that includes one or more collections of available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0115] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only one way, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0116] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0117] In the description of this specification, the description with reference to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0118] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not elaborate on all details, nor do they limit the present invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. The present specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. The dance movement teaching method based on movement perception is characterized by: The specific steps include: S1. Collect students' physiological data during dance training and evaluate dance difficulty according to dance difficulty evaluation strategy; S2, collecting the movement data of students after completing the training unit, and evaluating the neatness of students during training according to the dance neatness evaluation strategy; S3, collecting images of students during dance training in real time, and evaluating the standard of students' dance during training according to the dance posture evaluation model; S4, evaluating the overall situation of dance teaching based on the dance difficulty, dance uniformity and dance accuracy; S5. Determine whether the dance teacher needs to teach again based on the comprehensive dance teaching situation.

2. The dance movement teaching method based on movement perception as claimed in claim 1, characterized in that: The S1 comprises the following specific steps: S11, collecting physiological data of students during dance training, wherein the physiological data includes heart rate, respiratory rate and energy consumption; S12, introducing the heart rate, respiratory rate and energy consumption into a dance complexity value calculation formula to calculate the dance complexity value, wherein the dance complexity value calculation formula is: Where λ1 is the heart rate coefficient, λ2 is the respiratory rate coefficient, λ3 is the energy consumption coefficient, λ1>0,λ2>0,λ3>0 and λ1+λ2+λ3=1, H ij is the heart rate of the i-th student in the j-th time period, H bz is the standard heart rate in a unit time period, B ij is the breathing frequency of the i-th student in the j-th time period, B bz is the standard respiratory rate in a unit time period, X ij is the energy consumption of the i-th student in the j-th time period, X bz is the standard energy consumption in a unit time period, I is the total number of students collected, and J is the total number of time periods collected.

3. The dance movement teaching method based on movement perception as claimed in claim 2 is characterized in that: The S2 comprises the following specific steps: S21, dividing the training dance into several training units, collecting the student's motion data when the training unit is completed, the motion data including coordinates and completion time, the coordinates including the student's head coordinates, hand coordinates and foot coordinates; S22, importing the head coordinates, hand coordinates and foot coordinates of a single student in the set training unit into the action offset value calculation formula to calculate the action offset value of the student, the action offset value calculation formula is: In the formula, θ h is the angle of the hth part of the student, is the standard angle of the hth part; S23, importing the action offset value and the completion time into a dance uniformity calculation formula to calculate the dance uniformity, the dance uniformity calculation formula is: Where α1 is the action offset ratio, α2 is the completion time ratio, α1>0, α2>0 and α1+α2=1, is the action offset value of the nth training unit of the ith student, N is the total number of training units, is the average action offset value of the nth training unit, T in is the completion time of the nth training unit for the i-th student, is the standard completion time of the nth training unit.

4. The dance movement teaching method based on movement perception as claimed in claim 3 is characterized in that: The S3 comprises the following specific steps: S31, collecting images of students during dance training in real time, and extracting key points from the images; S32, importing the key points into the dance posture standard value calculation formula to calculate the standard value of the dance during the student training, the dance posture standard value calculation formula is: Where S is the standard posture sequence, S = {S1, S2, ..., S p }, where S p The posture features of the standard posture sequence with time frame p, namely S p =((x1,y1),(x2,y2),...,(x k ,y k ), Z is the posture sequence to be measured, Z={Z1,Z2,...,Z p }, where Z p The posture feature of the posture sequence to be tested with time frame p, that is, Z p =((x 11 ,y 11 ),(x 12 ,y 12 ),...,(x 1k ,y 1k ), DTW(S,Z) is the DTW distance between sequences S and T, DTW′ is the standard DTW distance, ΔS pm is the displacement vector of the mth key point in the pth time frame in the standard action sequence, ΔZ pm is the displacement vector of the mth key point in the pth time frame in the action sequence to be tested, ||*||2 is the Euclidean distance, P is the total number of time frames, M is the total number of key points in the posture features of a single time frame, L′ is the standard distance of the key points, and exp(*) is an exponential function with the real number e as the base.

5. The dance movement teaching method based on movement perception as claimed in claim 4 is characterized in that: The S4 comprises the following specific steps: The dance complexity value, dance uniformity and dance posture standard value are introduced into the dance teaching comprehensive evaluation value calculation formula to calculate the dance teaching comprehensive evaluation value. The dance teaching comprehensive evaluation value calculation formula is: Where β1 is the coefficient of dance complexity, β2 is the coefficient of dance uniformity, β3 is the coefficient of dance posture standard value, β1>0, β2>0, β3>0 and β1+β2+β3=1, D b i z is the standard value of the dance posture of the i-th student.

6. The dance movement teaching method based on movement perception as claimed in claim 5, characterized in that: The S5 comprises the following specific steps: Compare the dance teaching comprehensive evaluation value with the preset dance teaching comprehensive threshold value. If the dance teaching comprehensive evaluation value is less than the preset dance teaching comprehensive threshold value, it is judged that the dance student can learn autonomously. If the comprehensive evaluation value of dance teaching is greater than or equal to the preset comprehensive threshold value of dance teaching, it is judged that the dance needs to be taught again by the dance teacher.

7. A dance movement teaching system based on motion perception, used to implement the dance movement teaching method based on motion perception as claimed in any one of claims 1 to 6, characterized in that: It includes a control module, a data acquisition module, a difficulty assessment module, a neatness assessment module, a picture processing module, a posture assessment module, a comprehensive teaching assessment module and a comparison and judgment module; The data collection module is used to collect the physiological data of students during dance training and the movement data of students when completing the training unit; The difficulty assessment module is used to import the heart rate, breathing frequency and energy consumption into the dance complexity value calculation formula to calculate the dance complexity value; The neatness evaluation module is used to first import the coordinates into the action offset value calculation formula to calculate the student's action offset value, and then import the action offset value and completion time into the dance neatness calculation formula to calculate the dance neatness.

8. The dance movement teaching system based on movement perception as claimed in claim 7, characterized in that: The image processing module is used to collect images of students during dance training in real time and perform image preprocessing to extract key points; The posture evaluation module is used to import key points into the dance posture standard value calculation formula to calculate the standard value of the dance during the student training; The comprehensive teaching evaluation module is used to import the dance complexity value, dance uniformity and dance posture standard value into the dance teaching comprehensive evaluation value calculation formula to calculate the dance teaching comprehensive evaluation value; The comparison and judgment module is used to compare the dance teaching comprehensive evaluation value with the preset dance teaching comprehensive threshold value, and judge whether the dance teacher needs to teach again according to the comparison result.

9. The dance movement teaching system based on movement perception as claimed in claim 8, characterized in that: The control module is used to control the operation of the data acquisition module, the difficulty assessment module, the neatness assessment module, the image processing module, the posture assessment module, the comprehensive teaching assessment module and the comparison and judgment module.

Images