CN114333046A - Dance action scoring method, device, equipment and storage medium - Google Patents
Dance action scoring method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114333046A CN114333046A CN202111358056.0A CN202111358056A CN114333046A CN 114333046 A CN114333046 A CN 114333046A CN 202111358056 A CN202111358056 A CN 202111358056A CN 114333046 A CN114333046 A CN 114333046A
- Authority
- CN
- China
- Prior art keywords
- dance
- standard
- human body
- angle variation
- action
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention provides a dance action scoring method, a dance action scoring device, dance action scoring equipment and a dance action scoring storage medium, wherein the dance action scoring method comprises the following steps: inputting human body posture identification data of the dance motion of the current student into a human body identification model to obtain a first three-dimensional coordinate of a human body joint; acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate; acquiring a first angle variation of the first included angle between two adjacent frames of images; comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action in which the standard angle variation is located; and acquiring the differential scores of different parts of the human body of the current student according to the angle variation difference and the grading rule corresponding to the current dance type. According to the technical scheme, dance actions can be scored accurately.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a dance action scoring method and device, electronic equipment and a non-transitory computer-readable storage medium.
Background
Dance slowly enters the daily lives of a greater number of people as a fitness exercise. In the current dance exercise process, the dance student needs to use the mirror to carry out the self-observation of whether the dance action is in place or not so as to carry out self-adjustment, or a dance coach judges whether the dance student action is in place or not.
However, it is not possible to accurately compare the dancing movements of a dancing student with standard dancing movements, whether the dancing student himself or a dancing coach.
Disclosure of Invention
The invention provides a dance action scoring method, a dance action scoring device, electronic equipment and a non-transitory computer readable storage medium, which are used for solving the problem that dance actions cannot be accurately compared in the prior art and achieving accurate scoring of dance actions.
The invention provides a dance action scoring method, which comprises the following steps: inputting human body posture identification data of the dance motion of the current student into a human body identification model to obtain a first three-dimensional coordinate of a human body joint; acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate; acquiring a first angle variation of the first included angle between two adjacent frames of images; comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action in which the standard angle variation is located; and acquiring the differential scores of different parts of the human body of the current student according to the angle variation difference and the grading rule corresponding to the current dance type.
According to the dance action scoring method provided by the invention, after the differential scores of different parts of the human body of the current student are obtained according to the angle variation difference and the scoring rule corresponding to the current dance type, the method further comprises the following steps: and generating a front-end display page according to the angle variation difference and the standard action data of the standard action so as to compare and display the dance action of the current student and the standard action.
According to the dance motion scoring method provided by the invention, before inputting the human body posture recognition data of the dance motion of the current student into the human body recognition model, the method further comprises the following steps: and inputting the dance video of the current student to a preset human posture recognition model to obtain the human posture recognition data.
According to the dance action scoring method provided by the invention, the generating of the front-end display page according to the angle variation difference and the standard action data of the standard action comprises the following steps: carrying out normalization processing on the angle variation difference to obtain a normalized difference; and generating a connecting line dot diagram by using a drawing protocol according to the normalized difference value and the standard action data, wherein dots of the connecting line dot diagram are superposed on corresponding positions of corresponding frames of the standard video of the standard action.
According to the dance action scoring method provided by the invention, the step of generating a connecting line circular point diagram by using a drawing protocol according to the normalized difference value and the standard action data comprises the following steps: and changing the display colors of the dots of the connecting dot diagram and the connecting lines according to the angle variation difference value and the set color rule.
According to the dance action scoring method provided by the invention, before inputting the dance video of the student of the current student into the preset human body posture recognition model, the method further comprises the following steps: and acquiring the dance video of the student, which is obtained by performing video acquisition on the dance motion of the current student.
According to the dance motion scoring method provided by the invention, before comparing the first angle variation with the standard angle variation of the standard motion, the method further comprises: acquiring a standard dance video obtained by performing video acquisition on dance movements of a standard dancer; inputting the human body posture recognition data of the dance motions of the standard dancer obtained according to the standard dance video into a human body recognition model to obtain a second three-dimensional coordinate of a human body joint; acquiring a second included angle between two connected bones of the human body in the same frame of image according to the second three-dimensional coordinate; and acquiring the standard angle variation of the second included angle between two adjacent frames of images.
The invention provides a dance action scoring device, comprising: the first recognition unit is used for inputting human body posture recognition data of the dance motion of the current student into the human body recognition model to obtain a first three-dimensional coordinate of a human body joint; the first acquisition unit is used for acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate; the second acquisition unit is used for acquiring a first angle variation of the first included angle between two adjacent frames of images; the comparison unit is used for comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action where the standard angle variation is located; and the scoring unit is used for acquiring the differentiation scores of different parts of the human body of the current student according to the angle variation difference and a scoring rule corresponding to the current dance type.
According to the dance action scoring device provided by the invention, the device further comprises a display unit, wherein the display unit is used for generating a front-end display page according to the angle variation difference and the standard action data of the standard action so as to compare and display the dance action of the current student and the standard action.
According to the dance action grading device provided by the invention, the device further comprises a second recognition unit, wherein the second recognition unit is used for inputting the dance video of the current student to a preset human posture recognition model to obtain the human posture recognition data.
According to the dance action scoring device provided by the invention, the display unit is further used for carrying out normalization processing on the angle variation difference to obtain a normalized difference; and generating a connecting line dot diagram by using a drawing protocol according to the normalized difference value and the standard action data, wherein dots of the connecting line dot diagram are superposed on corresponding positions of corresponding frames of the standard video of the standard action.
According to the dance action scoring device provided by the invention, the display unit is further used for: and changing the display colors of the dots of the connecting dot diagram and the connecting lines according to the angle variation difference value and the set color rule.
According to the dance action scoring device provided by the invention, the device further comprises a third acquisition unit, wherein the third acquisition unit is used for acquiring the dance video of the student, which is obtained by performing video acquisition on the dance action of the current student.
According to the dance action grading device provided by the invention, the device further comprises a standard unit, a standard dance video and a standard dance processing unit, wherein the standard dance video is used for acquiring the dance action of a standard dancer; inputting the human body posture recognition data of the dance motions of the standard dancer obtained according to the standard dance video into a human body recognition model to obtain a second three-dimensional coordinate of a human body joint; acquiring a second included angle between two connected bones of the human body in the same frame of image according to the second three-dimensional coordinate; and acquiring the standard angle variation of the second included angle between two adjacent frames of images.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the dance motion scoring method.
The present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the dance motion scoring methods described above.
According to the dance action grading method, the dance action grading device, the electronic equipment and the non-transitory computer readable storage medium, the position coordinates of the human body joints are obtained by recognizing the human body posture and the human body of the current dance action of the student, the bone angle variation quantity in two adjacent frames of images can be obtained according to the position coordinates of different human body joints, the bone angle variation quantity is compared with the standard angle variation quantity, and the grading of the current dance action can be obtained by combining the dance grading rule. This scheme can obtain comparatively accurate dance score.
The technical scheme of the embodiment of the invention provides a convenient and intelligent auxiliary tool for dance learning, and the computer automatically compares and scores actions according to video information or shot pictures, so that dance learning of students becomes more convenient and the error correction effect is better under the condition that most of dance coaches do not have field instruction. In addition, the technical scheme of the embodiment of the invention provides an objective auxiliary scoring means for dance examination grades, provides an objective scoring mechanism for some dance basic actions on the basis of manual scoring, and increases a judgment reference mode for organizers of dance examination grades.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a dance movement scoring method provided by the present invention;
FIG. 2 is a schematic flow chart of acquiring standard action data according to the present invention;
FIG. 3 is a schematic structural diagram of a dance motion scoring apparatus provided in the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the invention. As used in one or more embodiments of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present invention refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used herein to describe various information in one or more embodiments of the present invention, such information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first aspect may be termed a second aspect, and, similarly, a second aspect may be termed a first aspect, without departing from the scope of one or more embodiments of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The following detailed description of exemplary embodiments of the invention refers to the accompanying drawings.
FIG. 1 is a flow chart of a dance motion scoring method according to an embodiment of the present invention. The method provided by the embodiment of the invention can be executed by any electronic equipment with computer processing capability, such as a terminal or a server. As shown in fig. 1, the dance action scoring method includes:
and 102, inputting the human body posture identification data of the dance motion of the current student into the human body identification model to obtain a first three-dimensional coordinate of the human body joint.
Specifically, the human body posture recognition data refers to recognition data obtained by performing human body posture recognition on a human body in an image or a video through a human body posture recognition model. The human body posture recognition can be human body key point posture recognition, the position of each frame of human body posture key part is detected in the human body behavior expression process, the human body posture is simplified into human body key points, and the semantics expressed by the human body posture are classified and recognized through the key points. The key point in the embodiment of the invention can be a human joint. The human gesture recognition model may be a neural network model. The human recognition Model is a three-dimensional Model of a human body, such as an SMPL (A Skinned Multi-Person Linear Model) Model. The SMPL model is a skin and texture vertex-based model that can be easily adapted to accommodate a variety of human body shapes and poses.
And 104, acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate.
Specifically, the bones are connected through human joints, and the straight lines where the bones are located can be obtained through the coordinates of the human joints, so that the included angle between the straight lines where the two bones are located can be obtained.
And 106, acquiring a first angle variation of the first included angle between two adjacent frames of images.
Specifically, the first angle variation may be obtained according to a first angle between two bones in one frame of image and a first angle between the two bones in a next frame of image of the one frame of image.
And 108, comparing the first angle variation with the standard angle variation of the standard action to obtain an angle variation difference, wherein the first angle variation is matched with the action sequence segment of the dance action where the corresponding standard angle variation is located.
Specifically, the standard angle variation is obtained from the video of the same dance movement collected from the standard dancer, and the step of obtaining the angle variation difference from the video is similar to steps 102 to 108.
And step 110, acquiring differentiation scores of different parts of the human body of the current student according to the angle variation difference and a grading rule corresponding to the current dance type.
Specifically, the difference values of the allowed angle variation of different dance types are different, and according to the scoring rule corresponding to the current dance type, the score of the dance motion of the current student, that is, the differential score, can be obtained.
In the related technology, the comparison between the dance action and the standard action is mostly carried out manually, the magnitude and the angle of the dance action are determined manually by visual inspection, the accuracy is not high, the comparison standard is subjective, and therefore the score obtained by comparison is not accurate enough. In the technical scheme of the embodiment of the invention, dance actions are analyzed through a computer vision technology and a motion analysis technology, and the angle variation difference obtained through analysis is compared with standard actions for scoring, so that more accurate quantitative scoring and error correction guidance results can be obtained.
Before step 102, a trainee dance video obtained by video acquisition of the dance motion of the current trainee can be acquired, and the trainee dance video of the current trainee is input into a preset human body posture recognition model to obtain human body posture recognition data.
In particular, the video capture device may be a camera or a wearable device. The color depth camera can be used for capturing the dancing action of the human body, and the portable wearable device with the function of collecting the color depth image can also be used for capturing the dancing action of the human body. The lens of the video acquisition equipment is controlled by the computer, and the dancer stands in the visual field of the video acquisition equipment, so that the video acquisition equipment can shoot the dancing action of the dancer to form a video stream. The video stream is input into the human body posture recognition model, so that two-dimensional and three-dimensional parameters of human body motion can be obtained, and then the captured two-dimensional and three-dimensional parameters can be predicted and optimized by using a human body motion sequence coding engine.
In step 102, three-dimensional coordinates corresponding to the joints of the human body can be calculated according to the two-dimensional and three-dimensional parameters of the optimized human body motion.
In step 104, an included angle between every two bones of the human body in each frame of image can be calculated according to the three-dimensional coordinates of the human body joint, and further, in step 106, the variation of the included angle between two frames is calculated.
Before step 108, the standard angle change also needs to be obtained. The process comprises the following steps as shown in figure 2:
and step 202, acquiring a standard dance video obtained by performing video acquisition on dance movements of a standard dancer.
And step 204, inputting the human body posture recognition data of the dance motions of the standard dancer obtained according to the standard dance video into the human body recognition model to obtain a second three-dimensional coordinate of the human body joint.
And step 206, acquiring a second included angle between two connected bones of the human body in the same frame of image according to the second three-dimensional coordinate.
And step 208, acquiring the standard angle variation of the second included angle between two adjacent frames of images.
In addition, when the angle variation difference comparison is performed in step 108, it is required to time-align the first angle variation with the standard angle variation. In the embodiment of the invention, the method of Rule-Base can be used for segmenting the dance action segment of the human body. Therefore, the action sequences of the dancing student and the dancing coach are divided semantically, action sequence segments are separated and matched with the same action sequence segments of the dancing student and the dancing coach, and time alignment of the first angle variation and the corresponding standard angle variation is achieved.
In the angle comparison step in step 108, the angle variation of the dancing student and the dancing coach can be compared frame by frame for the stripped action segment to obtain the angle variation difference.
In the step 110, in the display step of action comparison, a front-end display page may be generated according to the angle variation difference and the standard action data of the standard action, so as to perform comparison display of the dance action of the current trainee and the standard action.
Specifically, the angle variation difference may be normalized to obtain a normalized difference; and generating a connecting line dot diagram by using a drawing protocol according to the normalized difference value and the standard action data, wherein dots of the connecting line dot diagram are superposed on corresponding positions of corresponding frames of the standard video of the standard action. The dots in the connecting dot diagram represent nodes, and the connecting lines represent bones.
During the normalization process, the angle variation difference is mapped to a range from-1 to 1, and is denoted as diff (k), where k is the current frame number. diff (k) is sent to a front-end program by the server, the front-end program renders nodes and bones on a picture by using OpenGL or WebGL, and the nodes and the bones are superposed on corresponding positions of human bodies in the video to realize the display of action contrast. OpenGL is a cross-language, cross-platform application programming interface for rendering 2D (two-dimensional), 3D (three-dimensional) vector graphics. WebGL is a drawing protocol. The connected dot graph may be generated using either OpenGL or WebGL.
In addition, the display colors of the dots of the dot diagram of the connecting line and the connecting line can be changed according to the difference value of the angle variation and the set color rule. Specifically, the normalized difference diff (k) may be multiplied by the corresponding value of the RGB color values to change the displayed color of the nodes and bones to provide a more intuitive displayed image.
According to the dance action scoring scheme, through a human body posture recognition link, a human body recognition model establishment link, a three-dimensional coordinate calculation link, a joint angle and dynamic information calculation link, a motion sequence cross-time matching and analyzing link, a dynamic information storage and calling link, an action comparison and scoring link and a client display rendering link, the semantic segmentation of dance actions is achieved, time calibration and alignment are achieved, and therefore accurate scoring data can be obtained.
In the embodiment of the invention, a dance learner and a dance coach respectively use the system and the product which carry the technology of the embodiment of the invention to record own dance motions, the algorithm can carry out matching and difference search according to the motions of two persons, and quantitative guidance results of scoring, evaluation and error correction are given, so that the learner can be helped to learn the dance motions.
The technical scheme of the embodiment of the invention provides a convenient and intelligent auxiliary tool for dance learning, and the computer automatically compares and scores actions according to video information or shot pictures, so that dance learning of students becomes more convenient and the error correction effect is better under the condition that most of dance coaches do not have field instruction. In addition, the technical scheme of the embodiment of the invention provides an objective auxiliary scoring means for dance examination grades, provides an objective scoring mechanism for some dance basic actions on the basis of manual scoring, and increases a judgment reference mode for organizers of dance examination grades.
According to the dance action grading method provided by the invention, the position coordinates of the human body joints are obtained by carrying out human body posture recognition and human body recognition on the dance action of the current student, the bone angle variation quantity in two adjacent frames of images can be obtained according to the position coordinates of different human body joints, the bone angle variation quantity is compared with the standard angle variation quantity, and the grading of the current dance action can be obtained by combining the dance grading rule. This scheme can obtain comparatively accurate dance score.
The dance movement scoring device provided by the invention is described below, and the dance movement scoring device described below and the dance movement scoring method described above can be referred to correspondingly.
As shown in fig. 3, a dance motion scoring apparatus according to an embodiment of the present invention includes:
the first recognition unit 302 may be configured to input human body posture recognition data of a dance motion of the current trainee into the human body recognition model, so as to obtain a first three-dimensional coordinate of a human body joint.
Specifically, the human body recognition Model is a three-dimensional Model of a human body, such as an SMPL (excited Multi-Person Linear Model) Model. The SMPL model is a skin and texture vertex-based model that can be easily adapted to accommodate a variety of human body shapes and poses.
The first obtaining unit 304 may be configured to obtain a first angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate.
Specifically, the straight line where the bones are located can be obtained through the coordinates of the human joints, and then the included angle between the straight lines where the two bones are located can be obtained.
The second obtaining unit 306 may be configured to obtain a first angle variation of the first angle between two adjacent frames of images.
Specifically, the first angle variation may be obtained according to a first angle between two bones in one frame of image and a first angle between the two bones in a next frame of image of the one frame of image.
The comparing unit 308 may be configured to compare the first angle variation with a standard angle variation of a standard motion to obtain an angle variation difference, where the first angle variation matches with a motion sequence segment of the dance motion where the corresponding standard angle variation is located.
The scoring unit 310 may be configured to obtain differentiation scores of different parts of the human body of the current learner according to the angle variation difference and a scoring rule corresponding to the current dance type.
In the related technology, the comparison between the dance action and the standard action is mostly carried out manually, the magnitude and the angle of the dance action are determined manually by visual inspection, the accuracy is not high, the comparison standard is subjective, and therefore the score obtained by comparison is not accurate enough. In the technical scheme of the embodiment of the invention, dance actions are analyzed through a computer vision technology and a motion analysis technology, and the angle variation difference obtained through analysis is compared with standard actions for scoring, so that more accurate quantitative scoring and error correction guidance results can be obtained.
In the embodiment of the present invention, the apparatus may further include a display unit, configured to generate a front-end display page according to the angle variation difference and the standard motion data of the standard motion, so as to perform comparative display of the dance motion of the current trainee and the standard motion.
In the embodiment of the present invention, the apparatus may further include a second recognition unit, configured to input the dance video of the current trainee into a preset human posture recognition model, so as to obtain human posture recognition data.
The key point in the embodiment of the invention can be a human joint. The human gesture recognition model may be a neural network model.
In the embodiment of the present invention, the display unit may be further configured to perform normalization processing on the angle variation difference to obtain a normalized difference; and generating a connecting line dot diagram by using a drawing protocol according to the normalized difference value and the standard action data, wherein dots of the connecting line dot diagram are superposed on corresponding positions of corresponding frames of the standard video of the standard action.
During the normalization process, the angle variation difference is mapped to a range from-1 to 1, and is denoted as diff (k), where k is the current frame number. diff (k) is sent to a front-end program by the server, the front-end program renders nodes and bones on a picture by using OpenGL or WebGL, and the nodes and the bones are superposed on corresponding positions of human bodies in the video to realize the display of action contrast.
In the embodiment of the present invention, the display unit may further be configured to: and changing the display colors of the dots of the dot diagram of the connecting line and the connecting line according to the angle variation difference and the set color rule.
In the embodiment of the present invention, the apparatus may further include a third obtaining unit, configured to obtain a dance video of the trainee, where the dance video of the trainee is obtained by performing video acquisition on a dance motion of the current trainee.
The lens of the video acquisition equipment is controlled by the computer, and the dancer stands in the visual field of the video acquisition equipment, so that the video acquisition equipment can shoot the dancing action of the dancer to form a video stream. And inputting the video stream into a human body posture recognition model, namely obtaining two-dimensional and three-dimensional parameters of human body motion, and then predicting and optimizing the captured two-dimensional and three-dimensional parameters by using a human body motion sequence coding engine.
In the embodiment of the invention, the device further comprises a standard unit, a dancing unit and a processing unit, wherein the standard unit is used for acquiring a standard dancing video obtained by video acquisition of dancing actions of a standard dancer; inputting the human body posture recognition data of the dance movement of the standard dancer obtained according to the standard dance video into the human body recognition model to obtain a second three-dimensional coordinate of the human body joint; acquiring a second included angle between two connected bones of the human body in the same frame of image according to the second three-dimensional coordinate; and acquiring the standard angle variation of the second included angle between two adjacent frames of images.
Further, the comparing unit requires time alignment of the first angle change amount with the standard angle change amount when performing comparison with respect to the angle change amount difference. In the embodiment of the invention, the method of Rule-Base can be used for segmenting the dance action segment of the human body. Therefore, the action sequences of the dancing student and the dancing coach are divided semantically, action sequence segments are separated and matched with the same action sequence segments of the dancing student and the dancing coach, and time alignment of the first angle variation and the corresponding standard angle variation is achieved.
The technical scheme of the embodiment of the invention provides a convenient and intelligent auxiliary tool for dance learning, and the computer automatically compares and scores actions according to video information or shot pictures, so that dance learning of students becomes more convenient and the error correction effect is better under the condition that most of dance coaches do not have field instruction. In addition, the technical scheme of the embodiment of the invention provides an objective auxiliary scoring means for dance examination grades, provides an objective scoring mechanism for some dance basic actions on the basis of manual scoring, and increases a judgment reference mode for organizers of dance examination grades.
For details that are not disclosed in the embodiments of the device of the present invention, please refer to the above-described embodiment of the dance motion scoring method of the present invention for the details that are not disclosed in the embodiments of the device of the present invention.
According to the dance action scoring device provided by the invention, the position coordinates of the human body joints are obtained by carrying out human body posture recognition and human body recognition on the dance action of the current student, the bone angle variation quantity in two adjacent frames of images can be obtained according to the position coordinates of different human body joints, the bone angle variation quantity is compared with the standard angle variation quantity, and the score of the current dance action can be obtained by combining the dance scoring rule. This scheme can obtain comparatively accurate dance score.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. Processor 410 may invoke logic instructions in memory 430 to perform a dance motion scoring method comprising: inputting human body posture identification data of the dance motion of the current student into a human body identification model to obtain a first three-dimensional coordinate of a human body joint; acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate; acquiring a first angle variation of the first included angle between two adjacent frames of images; comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action in which the standard angle variation is located; and acquiring the differential scores of different parts of the human body of the current student according to the angle variation difference and the grading rule corresponding to the current dance type.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, enable the computer to perform the dance action scoring method provided by the above methods, the method comprising: inputting human body posture identification data of the dance motion of the current student into a human body identification model to obtain a first three-dimensional coordinate of a human body joint; acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate; acquiring a first angle variation of the first included angle between two adjacent frames of images; comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action in which the standard angle variation is located; and acquiring the differential scores of different parts of the human body of the current student according to the angle variation difference and the grading rule corresponding to the current dance type.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the dance action scoring methods provided above, the method comprising: inputting human body posture identification data of the dance motion of the current student into a human body identification model to obtain a first three-dimensional coordinate of a human body joint; acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate; acquiring a first angle variation of the first included angle between two adjacent frames of images; comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action in which the standard angle variation is located; and acquiring the differential scores of different parts of the human body of the current student according to the angle variation difference and the grading rule corresponding to the current dance type.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A dance action scoring method is characterized by comprising the following steps:
inputting human body posture identification data of the dance motion of the current student into a human body identification model to obtain a first three-dimensional coordinate of a human body joint;
acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate;
acquiring a first angle variation of the first included angle between two adjacent frames of images;
comparing the first angle variation with a standard angle variation of a corresponding standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action in which the standard angle variation is located;
and acquiring the differential scores of different parts of the human body of the current student according to the angle variation difference and the grading rule corresponding to the current dance type.
2. The method according to claim 1, wherein after obtaining the differentiation scores of different parts of the human body of the current student according to the angle variation difference and the scoring rule corresponding to the current dance type, the method further comprises:
and generating a front-end display page according to the angle variation difference and the standard action data of the standard action so as to compare and display the dance action of the current student and the standard action.
3. The method of claim 1, wherein prior to inputting the human gesture recognition data for the dance movement of the current student into the human recognition model, the method further comprises:
and inputting the dance video of the current student to a preset human posture recognition model to obtain the human posture recognition data.
4. The method of claim 1, wherein generating a front-end display page according to the angle variation difference and standard motion data of the standard motion comprises:
carrying out normalization processing on the angle variation difference to obtain a normalized difference;
and generating a connecting line dot diagram by using a drawing protocol according to the normalized difference value and the standard action data, wherein dots of the connecting line dot diagram are superposed on corresponding positions of corresponding frames of the standard video of the standard action.
5. The method of claim 4, wherein generating a plot of a line circle using a mapping protocol based on the normalized difference values and the standard motion data comprises:
and changing the display colors of the dots of the connecting dot diagram and the connecting lines according to the angle variation difference value and the set color rule.
6. The method of claim 1, wherein before inputting the trainee dance video of the current trainee into a preset human posture recognition model, the method further comprises:
and acquiring the dance video of the student, which is obtained by performing video acquisition on the dance motion of the current student.
7. The method of claim 1, wherein prior to comparing the first angle change amount to a standard angle change amount of a standard action, the method further comprises:
acquiring a standard dance video obtained by performing video acquisition on dance movements of a standard dancer;
inputting the human body posture recognition data of the dance motions of the standard dancer obtained according to the standard dance video into a human body recognition model to obtain a second three-dimensional coordinate of a human body joint;
acquiring a second included angle between two connected bones of the human body in the same frame of image according to the second three-dimensional coordinate;
and acquiring the standard angle variation of the second included angle between two adjacent frames of images.
8. A dance action scoring device, comprising:
the first recognition unit is used for inputting human body posture recognition data of the dance motion of the current student into the human body recognition model to obtain a first three-dimensional coordinate of a human body joint;
the first acquisition unit is used for acquiring a first included angle between two connected bones of the human body in the same frame of image according to the first three-dimensional coordinate;
the second acquisition unit is used for acquiring a first angle variation of the first included angle between two adjacent frames of images;
the comparison unit is used for comparing the first angle variation with a standard angle variation of a standard action to obtain an angle variation difference, wherein the first angle variation is matched with a corresponding action sequence segment of the dance action where the standard angle variation is located;
and the scoring unit is used for acquiring the differentiation scores of different parts of the human body of the current student according to the angle variation difference and a scoring rule corresponding to the current dance type.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the processor executes the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111358056.0A CN114333046A (en) | 2021-11-16 | 2021-11-16 | Dance action scoring method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111358056.0A CN114333046A (en) | 2021-11-16 | 2021-11-16 | Dance action scoring method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114333046A true CN114333046A (en) | 2022-04-12 |
Family
ID=81044726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111358056.0A Pending CN114333046A (en) | 2021-11-16 | 2021-11-16 | Dance action scoring method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114333046A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112597933A (en) * | 2020-12-29 | 2021-04-02 | 咪咕互动娱乐有限公司 | Action scoring method and device and readable storage medium |
| CN116112761A (en) * | 2023-04-12 | 2023-05-12 | 海马云（天津）信息技术有限公司 | Method and device for generating virtual image video, electronic equipment and storage medium |
| CN116259111A (en) * | 2023-05-15 | 2023-06-13 | 江西工业贸易职业技术学院 | VR-based sports action scoring method, VR-based sports action scoring system, electronic device and storage medium |
-
2021
- 2021-11-16 CN CN202111358056.0A patent/CN114333046A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112597933A (en) * | 2020-12-29 | 2021-04-02 | 咪咕互动娱乐有限公司 | Action scoring method and device and readable storage medium |
| CN112597933B (en) * | 2020-12-29 | 2023-10-20 | 咪咕互动娱乐有限公司 | Action scoring method, device and readable storage medium |
| CN116112761A (en) * | 2023-04-12 | 2023-05-12 | 海马云（天津）信息技术有限公司 | Method and device for generating virtual image video, electronic equipment and storage medium |
| CN116112761B (en) * | 2023-04-12 | 2023-06-27 | 海马云（天津）信息技术有限公司 | Method and device for generating virtual image video, electronic equipment and storage medium |
| CN116259111A (en) * | 2023-05-15 | 2023-06-13 | 江西工业贸易职业技术学院 | VR-based sports action scoring method, VR-based sports action scoring system, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3885965B1 (en) | Image recognition method based on micro facial expressions, apparatus and related device | |
| CN114333046A (en) | Dance action scoring method, device, equipment and storage medium | |
| JP4829141B2 (en) | Gaze detection apparatus and method | |
| CN110363867B (en) | Virtual decorating system, method, device and medium | |
| WO2019245768A1 (en) | System for predicting articulated object feature location | |
| JP7015152B2 (en) | Processing equipment, methods and programs related to key point data | |
| CN108734078B (en) | Image processing method, image processing apparatus, electronic device, storage medium, and program | |
| CN110544301A (en) | Three-dimensional human body action reconstruction system, method and action training system | |
| KR20170002100A (en) | Method for providng smart learning education based on sensitivity avatar emoticon, and smart learning education device for the same | |
| CN114120432A (en) | Online learning attention tracking method based on sight estimation and application thereof | |
| CN112633221A (en) | Face direction detection method and related device | |
| CN112699857A (en) | Living body verification method and device based on human face posture and electronic equipment | |
| CN112417142A (en) | Auxiliary method and system for generating word meaning and abstract based on eye movement tracking | |
| Amrutha et al. | Human Body Pose Estimation and Applications | |
| Mattos et al. | Multi-view mouth renderization for assisting lip-reading | |
| CN112085223A (en) | Guidance system and method for mechanical maintenance | |
| US11527090B2 (en) | Information processing apparatus, control method, and non-transitory storage medium | |
| Purps et al. | Reconstructing facial expressions of HMD users for avatars in VR | |
| CN115019396A (en) | Learning state monitoring method, device, equipment and medium | |
| CN114677476A (en) | Face processing method and device, computer equipment and storage medium | |
| CN111274854B (en) | Human body action recognition method and vision enhancement processing system | |
| JP5688514B2 (en) | Gaze measurement system, method and program | |
| KR20130081126A (en) | Method for hand-gesture recognition and apparatus thereof | |
| CN112784631A (en) | Method for recognizing face emotion based on deep neural network | |
| CN113342157A (en) | Eyeball tracking processing method and related device |
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 |