CN108509924B - Human body posture scoring method and device - Google Patents
Human body posture scoring method and device Download PDFInfo
- Publication number
- CN108509924B CN108509924B CN201810301255.XA CN201810301255A CN108509924B CN 108509924 B CN108509924 B CN 108509924B CN 201810301255 A CN201810301255 A CN 201810301255A CN 108509924 B CN108509924 B CN 108509924B
- Authority
- CN
- China
- Prior art keywords
- human body
- scoring
- matrix
- audio
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure relates to the field of artificial intelligence technology. In order to solve the problems that scoring cannot be performed through each interactive link and scoring is not accurate in the existing human-computer interaction virtual enhanced display technology, the embodiment of the disclosure provides a scoring method and a scoring device for human body gestures, wherein the device comprises a receiving module used for receiving human body gesture data; the analysis and reading module is used for analyzing and reading the audio and video scoring parameters; and the scoring module is used for scoring the human body posture data according to the audio and video scoring parameters.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, in particular to a human body posture scoring method and device.
Background
The combination of the virtual enhanced display technology and the human-computer interaction is more and more intimate, and the use occasions are more and more. However, most of the existing scoring mechanisms are set rules, and the scoring mode is judged only according to results, and cannot reflect details in each interaction link, so that the finishing state and the interaction effect of the human body posture based on the virtual enhanced display technology cannot be accurately and fully reflected through the scoring mode.
Disclosure of Invention
The embodiment of the disclosure provides a human body posture scoring method and device.
In a first aspect, an embodiment of the present disclosure provides a method for scoring a human body posture, including the following steps: receiving human body posture data; analyzing and reading the audio and video scoring parameters; grading the human body posture data according to the audio and video grading parameters; and the application program for analyzing and reading the audio and video scoring parameters adopts a virtual enhanced display technology.
In a second aspect, the disclosed embodiments provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method described above.
In a third aspect, the disclosed embodiments provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method described above when executing the program.
In a fourth aspect, an embodiment of the present disclosure provides a human body posture scoring device, including: the receiving module is used for receiving human body posture data; the analysis and reading module is used for analyzing and reading the audio and video scoring parameters; the scoring module is used for scoring the human body posture data according to the audio and video scoring parameters; the analysis and reading module adopts a virtual enhanced display technology to the application program for analyzing and reading the audio and video scoring parameters.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and are intended to provide further explanation of the claimed technology.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced as follows:
fig. 1 is a schematic diagram of a hardware structure of a terminal device according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a human body posture scoring device according to a first embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating the operation of the human body posture scoring device shown in FIG. 2;
fig. 4 is a schematic structural diagram of a human body posture scoring device according to a second embodiment of the present disclosure;
FIG. 5 is a flowchart illustrating the operation of the human body posture scoring device shown in FIG. 4;
fig. 6 is a schematic structural diagram of a human body posture scoring device according to a third embodiment of the present disclosure;
FIG. 7 is a flowchart illustrating the operation of the human body posture scoring device shown in FIG. 6;
FIG. 8 is a hardware block diagram of a human body posture scoring device according to an embodiment of the present disclosure;
fig. 9 is a schematic diagram of a computer-readable storage medium of an embodiment of the disclosure.
Detailed Description
The present application will now be described in further detail with reference to the accompanying drawings and examples.
In the following description, the terms "first" and "second" are used for descriptive purposes only and are not intended to indicate or imply relative importance. The following description provides embodiments of the disclosure, which may be combined or substituted for various embodiments, and this application is therefore intended to cover all possible combinations of the same and/or different embodiments described. Thus, if one embodiment includes feature A, B, C and another embodiment includes feature B, D, then this application should also be considered to include an embodiment that includes one or more of all other possible combinations of A, B, C, D, even though this embodiment may not be explicitly recited in text below.
As shown in fig. 1, the terminal device may be implemented in various forms, and the terminal device in the present disclosure may include, but is not limited to, mobile terminal devices such as a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation apparatus, a vehicle-mounted terminal device, a vehicle-mounted display terminal, a vehicle-mounted electronic rear view mirror, and the like, and fixed terminal devices such as a digital TV, a desktop computer, and the like.
In one embodiment of the present disclosure, the terminal device may include a wireless communication unit 1, an a/V (audio/video) input unit 2, a user input unit 3, a sensing unit 4, an output unit 5, a memory 6, an interface unit 7, a controller 8, and a power supply unit 9, and the like. The a/V (audio/video) input unit 2 includes, but is not limited to, a camera, a front camera, a rear camera, and various audio/video input devices. It will be appreciated by those skilled in the art that the above embodiments list components included in the terminal device, and that fewer or more components than those described above may be included.
Those skilled in the art will appreciate that the various embodiments described herein can be implemented using a computer-readable medium such as computer software, hardware, or any combination thereof. For a hardware implementation, the embodiments described herein may be implemented using at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, an electronic unit designed to perform the functions described herein, and in some cases, such embodiments may be implemented in a controller. For a software implementation, the implementation such as a process or a function may be implemented with a separate software module that allows performing at least one function or operation. The software codes may be implemented by software applications (or programs) written in any suitable programming language, which may be stored in memory and executed by the controller.
Specifically, the embodiment of the present disclosure provides a scoring device for human body gestures, including: receiving human body posture data; analyzing and reading the audio and video scoring parameters; grading the human body posture data according to the audio and video grading parameters; the application program for analyzing and reading the audio and video scoring parameters adopts a virtual enhanced display technology. It can be understood that the present disclosure relates to a human body posture scoring device, and in particular to a human body posture scoring device based on a terminal device, where the terminal device includes but is not limited to: a mobile terminal, a fixed terminal or a vehicle-mounted terminal, etc.
It should be noted that, the received human body posture data may be captured by an optical camera device, such as a camera of a mobile terminal, kinect, etc., or the human body posture data of the detection area may be captured by a motion information collecting module, including but not limited to a displacement sensor, such as a displacement gyroscope, collecting angular velocities and displacements on three axes of a three-dimensional space, so as to calculate a distance, an acceleration sensor, such as a gravitational acceleration sensor, collecting acceleration parameters on three axes of the three-dimensional space, thereby calculating a motion acceleration and a motion direction by a plurality of acceleration parameters, an optical tracking sensor, and a position defining module. The position defining module is used for setting the position of each sensor and can be used as basic data for processing action signals of the sensors at different positions at the information data end.
The scoring device for the human body posture disclosed in the embodiment of the disclosure receives the human body posture data through the receiving module, and analyzes and reads the audio/video scoring parameters through the analyzing and reading module; grading the human body posture data according to the audio and video grading parameters by the grading module; the analysis and reading module analyzes and reads the audio and video scoring parameters, and the virtual enhanced display technology is adopted for the application program. The beneficial effects that scoring is accurate in a human-computer interaction virtual enhanced display state by acquiring human body posture data and analyzing and reading audio and video scoring parameters are achieved, and meanwhile, strong interactivity and experience of human-computer interaction are achieved. In addition, the device completes the beneficial effect of scoring accuracy in the human-computer interaction virtual enhanced display state by receiving human body gesture data and analyzing and reading audio/video scoring parameters, and meanwhile, realizes strong interactivity and experience of human-computer interaction.
Example one
As shown in fig. 2, the scoring device for human body posture of the present embodiment includes: the receiving module 200 is used for receiving human body posture data; the analysis and reading module 400 is used for analyzing and reading the audio/video scoring parameters, wherein a virtual enhanced display technology is adopted for an application program for analyzing and reading the audio/video scoring parameters; the scoring module 600 is configured to score the human body posture data according to the audio/video scoring parameters.
In this embodiment, the receiving module 200 is further configured to receive angle data of front legs and rear legs of a human body, angle data of arms and a body main body of the human body, and angle data of arms and a head of the human body. Therefore, the multi-angle of the receiving module for receiving data is improved.
In addition, it should be noted that the human body posture data of the detection area can be captured by an optical camera device, such as a camera of a mobile terminal, a kinect, etc., or the human body posture data of the detection area can be captured by a motion information collecting module, including but not limited to a displacement sensor, such as a displacement gyroscope, to collect angular velocities and displacements on three axes of a three-dimensional space, so as to calculate a distance, an acceleration sensor, such as a gravitational acceleration sensor, to collect acceleration parameters on three axes of the three-dimensional space, so as to calculate a motion acceleration and a motion direction by a plurality of acceleration parameters, an optical tracking sensor, and a position defining module. The position defining module is used for setting the position of each sensor and can be used as basic data for processing action signals of the sensors at different positions at the information data end.
Further, the scoring module 600 scores the human body posture data according to the audio/video scoring parameters. In order to improve the scoring accuracy, in addition to the algorithm mentioned in the disclosure, the human posture of the detection area can be captured by pre-establishing a human posture template and an optical recording device, such as a camera of a mobile terminal, a kinect and the like, and the human posture captured by the detection area is compared with the established human posture template, and the successfully compared human posture is an effective posture.
Establishing a human posture template gymnastics as follows: the estimation based on the human body posture is based on the binding of the human body posture and the human body key points. Specifically, the estimation based on the body posture mainly refers to obtaining the position, size, direction and the like of each body part, namely, the body component, such as the head, the left arm, the right arm, the upper arm and the like, in the input picture. In order to detect the human body posture from the input picture, the input picture must be scanned; since the sizes and the position distribution of the human body parts in the picture are not fixed, the scanning needs to be performed at different positions, sizes and directions when each human body part is scanned. And then, sending the scanned features to a binary classifier for detection so as to judge whether the human body is present. It will be appreciated that prior to detection, a binary classifier needs to be trained to obtain the parameters of the classifier. It should be noted that, during the detection, the same human body in the input image may be detected as a plurality of different but very similar gestures, so that the classification result needs to be fused to eliminate the repeated gestures.
Further, the generation of the pre-stored body pose-based template may also be based on a graph structure model employed for the estimation of the body pose of the component. The graph structure model is mainly divided into a graph model, an observation model of a component and a graph reasoning part. The graph model represents a human body architecture and is used for describing the overall constraint relation of all human body components, the graph model generally adopts a tree model, and the constraint relation of each pair of adjacent components adopts a deformation model between the components for modeling; establishing a model for the appearance of the human body part by the observation model of the part, wherein the quality of the appearance model of the part is determined by the quality of feature selection; and the diagram reasoning is to estimate the human body posture in the picture to be detected by utilizing the established diagram model and the component observation model. Before graph reasoning is carried out, parameters of the human body model are obtained through classifier training.
It should be noted that the human body model based on the component generally employs a skeleton model or a hinge shape model. The skeleton model, i.e. stick figure model, is composed of the middle axis line segments of human body parts, and the line segments are generally connected with each other. The skeleton model is simple and visual; the hinge type shape model generally uses a rectangle to represent a human body part, and the hinge type shape model contains more information quantity than a skeleton model, so that the position of the human body part can be described, the width information of the human body part can also be described, and a foundation is laid for subsequent comparison by enhancing the describable quantity.
Furthermore, after the estimation operation of the human body posture is completed, the human body key points are selected. Wherein, a plurality of arbitrary skeleton key points are selected to the key point, and a plurality of arbitrary skeleton key points can be: head, right shoulder, right elbow, right wrist, right hand, left shoulder, left elbow, left wrist, left hand, right knee, right ankle, right foot, left knee, left ankle, left foot, right hip, left hip. Binding any of the plurality of skeletal key points to the action event based on the body pose estimate. Therefore, accurate data support is provided for a follow-up user to execute the action event of the template based on the human body posture, and the method has good usability.
In this embodiment, the receiving module receives angle data of front legs and rear legs of a human body, angle data of arms and a body main body of the human body, and angle data of arms and a head of the human body. Therefore, reference of data diversity is provided for scoring the human body posture data according to the audio and video scoring parameters subsequently, and multi-dimensional data support is provided for scoring accuracy.
Fig. 3 is a flowchart illustrating the operation of the human body posture scoring device shown in fig. 2. The method comprises the following specific steps:
In this embodiment, receiving human body posture data includes: receiving angle data of front legs and rear legs of a human body, receiving angle data of arms and a body main body of the human body, and receiving angle data of the arms and the head of the human body.
And step 204, analyzing and reading the audio and video scoring parameters. The application program for analyzing and reading the audio and video scoring parameters adopts a virtual enhanced display technology.
And step 206, scoring the human body posture data according to the audio and video scoring parameters.
The scoring method for the human body posture disclosed by the embodiment of the disclosure receives human body posture data; analyzing and reading the audio and video scoring parameters; and scoring the human body posture data according to the audio and video scoring parameters. According to the method, the beneficial effect of accurate scoring in the human-computer interaction virtual enhanced display state is achieved by acquiring and analyzing the human body posture data and reading the audio and video scoring parameters, and meanwhile, the strong interactivity and the experience of the human-computer interaction are achieved.
In this embodiment, the angle data of the front leg and the rear leg of the human body, the angle data of the arm and the body main body of the human body, and the angle data of the arm and the head of the human body are received. Therefore, reference of data diversity is provided for scoring the human body posture data according to the audio and video scoring parameters subsequently, and multi-dimensional data support is provided for scoring accuracy.
The scoring method for the human body posture disclosed by the embodiment of the disclosure receives human body posture data; analyzing and reading the audio and video scoring parameters; and scoring the human body posture data according to the audio and video scoring parameters. According to the method, the beneficial effect of accurate scoring in the human-computer interaction virtual enhanced display state is achieved by acquiring and analyzing the human body posture data and reading the audio and video scoring parameters, and meanwhile, the strong interactivity and the experience of the human-computer interaction are achieved.
Example two
As shown in fig. 4, the human body posture scoring device of the present embodiment is different from the first embodiment in that a weight assignment module 300, a first calculation module 700, a second calculation module 800, and a third calculation module 900 are added to the device. Specifically, the receiving module 200 is configured to receive human body posture data; the weight assignment module 300 is used for performing weight assignment on the plurality of groups of acquired human posture data, assigning a first weight value to the angle data of the front legs and the rear legs of the human body, assigning a second weight value to the angle data of the arms and the main body of the human body, and assigning a third weight value to the angle data of the arms and the head of the human body; the analysis and reading module 400 is used for analyzing and reading the audio/video scoring parameters; the scoring module 600 is used for scoring the human body posture data according to the audio/video scoring parameters; the first calculating module 700 is configured to multiply the first weight value, the second weight value, and the third weight value with a weight value of a preset standard template, respectively, to obtain a first product, a second product, and a third product; the second calculation module 800 is configured to multiply the first product, the second product, and the third product by depth values of the human front leg and the human rear leg, depth values of the human arm and the body main body, and depth values of the human arm and the head angle, respectively; the third calculating module 900 is configured to sum and average the obtained products, and complete scoring on the human body posture data by combining the audio/video scoring parameters.
In this embodiment, due to the addition of the weight assignment module, the first calculation module, the second calculation module and the third calculation module, accurate data support is provided for the accuracy of the scoring of the human body posture based on the virtual augmented display technology.
Fig. 5 is a flowchart illustrating the operation of the human body posture scoring device shown in fig. 4. The specific process steps are as follows:
And step 403, analyzing and reading the audio/video scoring parameters. The application program for analyzing and reading the audio and video scoring parameters adopts a virtual enhanced display technology.
And 406, summing and averaging the obtained products, and finishing scoring on the human body posture data by combining the audio and video scoring parameters.
In the embodiment, the human body posture data are scored according to the audio and video scoring parameters. Specifically, in addition to the algorithm mentioned in the present disclosure, the human posture of the detection region may be captured by an optical recording device, such as a camera of the mobile terminal, a kinect, or the like, by establishing a human posture template in advance, and the human posture captured by the detection region is compared with the established human posture template, and the successfully compared human posture is an effective posture.
Establishing a human posture template gymnastics as follows: the estimation based on the human body posture is based on the binding of the human body posture and the human body key points. Specifically, the estimation based on the body posture mainly refers to obtaining the position, size, direction and the like of each body part, namely, the body component, such as the head, the left arm, the right arm, the upper arm and the like, in the input picture. In order to detect the human body posture from the input picture, the input picture must be scanned; since the sizes and the position distribution of the human body parts in the picture are not fixed, the scanning needs to be performed at different positions, sizes and directions when each human body part is scanned. And then, sending the scanned features to a binary classifier for detection so as to judge whether the human body is present. It will be appreciated that prior to detection, a binary classifier needs to be trained to obtain the parameters of the classifier. It should be noted that, during the detection, the same human body in the input image may be detected as a plurality of different but very similar gestures, so that the classification result needs to be fused to eliminate the repeated gestures.
Further, the generation of the pre-stored body pose-based template may also be based on a graph structure model employed for the estimation of the body pose of the component. The graph structure model is mainly divided into a graph model, an observation model of a component and a graph reasoning part. The graph model represents a human body architecture and is used for describing the overall constraint relation of all human body components, the graph model generally adopts a tree model, and the constraint relation of each pair of adjacent components adopts a deformation model between the components for modeling; establishing a model for the appearance of the human body part by the observation model of the part, wherein the quality of the appearance model of the part is determined by the quality of feature selection; and the diagram reasoning is to estimate the human body posture in the picture to be detected by utilizing the established diagram model and the component observation model. Before graph reasoning is carried out, parameters of the human body model are obtained through classifier training.
It should be noted that the human body model based on the component generally employs a skeleton model or a hinge shape model. The skeleton model, i.e. stick figure model, is composed of the middle axis line segments of human body parts, and the line segments are generally connected with each other. The skeleton model is simple and visual; the hinge type shape model generally uses a rectangle to represent a human body part, and the hinge type shape model contains more information quantity than a skeleton model, so that the position of the human body part can be described, the width information of the human body part can also be described, and a foundation is laid for subsequent comparison by enhancing the describable quantity.
Furthermore, after the estimation operation of the human body posture is completed, the human body key points are selected. Wherein, a plurality of arbitrary skeleton key points are selected to the key point, and can be: head, right shoulder, right elbow, right wrist, right hand, left shoulder, left elbow, left wrist, left hand, right knee, right ankle, right foot, left knee, left ankle, left foot, right hip, left hip. Binding any of the plurality of skeletal key points to the action event based on the body pose estimate. Therefore, accurate data support is provided for a follow-up user to execute the action event of the template based on the human body posture, and the method has good usability.
The scoring method for the human body posture disclosed by the embodiment of the disclosure receives human body posture data; analyzing and reading the audio and video scoring parameters; and scoring the human body posture data according to the audio and video scoring parameters. According to the method, the beneficial effect of accurate scoring in the human-computer interaction virtual enhanced display state is achieved by receiving and analyzing the human body posture data and reading the audio and video scoring parameters, and meanwhile, the strong interactivity and the experience of the human-computer interaction are achieved.
In the embodiment, because the obtained multiple groups of human body posture data are subjected to weight assignment, the angle data of the front legs and the rear legs of the human body are assigned with a first weight value, the angle data of the arms and the main body of the human body are assigned with a second weight value, and the angle data of the arms and the head of the human body are assigned with a third weight value; and calculating the numerical values and the weight values of the preset standard templates, the depth values of the human front legs and the human back legs, the depth values of the human arms and the human body main body and the depth values of the human arms and the head angles, and providing accurate data support for the scoring accuracy of the human posture based on the virtual enhanced display technology.
EXAMPLE III
As shown in fig. 6, a difference of the human body posture scoring device in this embodiment from the first embodiment is that the device, in addition to adding the weight assignment module 300, the first calculation module 700, the second calculation module 800 and the third calculation module 900, further includes the parsing and reading module 400: the acquisition unit 401 is configured to acquire sound characteristics and motion characteristics of a preset standard audio and video in an application program. The preset standard audio and video sound characteristics comprise: loudness, pitch, timbre and tempo; the action characteristics include: the action completion value, the action completion and audio and video rhythm matching ratio attribute value and the action completion time value.
It should be noted that, the scoring module 600 scores the human body posture data according to the audio/video scoring parameters, and includes: and calculating according to the action characteristic matrix and the preset grading matrixes of the man-machine interaction actions with different grades of difficulty to generate a final grading matrix of the user. Specifically, a motion feature vector for each motion is constructed for a plurality of attribute values for each motion. Wherein the plurality of attribute values for each action includes: an action completion degree attribute value and an action completion and music rhythm matching ratio attribute value. And forming a motion characteristic matrix of at least one motion by using the motion characteristic vector of each motion. And determining scoring matrixes of the human-computer interaction actions with different grades of difficulty, namely analyzing the bone node information and the bone node information of at least one human-computer interaction action of the human-computer interaction actions with different grades of difficulty and the matching ratio of the bone node information and the music rhythm, calculating the bone node information and the music rhythm to obtain the score of the human-computer interaction action of a certain grade, and forming the scoring matrixes according to the scores of the human-computer interaction actions with different grades of difficulty. Finally, determining the final score of the user according to the action characteristic matrix and the scoring matrix, specifically: and obtaining a product of the action characteristic matrix and a transposed matrix of the action characteristic matrix as a first matrix, summing the first matrix and an adjustment unit matrix to obtain a second matrix, wherein the adjustment unit matrix is the product of the unit matrix and an adjustment coefficient, the adjustment coefficient is a constant greater than 0, obtaining a product of an inverse matrix of the second matrix, the action characteristic matrix and the transposed matrix of the scoring matrix, and taking the product as the scoring matrix in the action characteristic space during the man-machine interaction process of a user of the terminal equipment.
In this embodiment, through the analysis and reading module 400, the addition of the acquisition unit 401 makes the analysis and reading of the audio/video scoring parameters more detailed and multidimensional, and lays a data foundation for the accuracy of scoring the human body posture data according to the audio/video scoring parameters.
Fig. 7 is a flowchart illustrating the operation of the human body posture scoring device shown in fig. 6. The method comprises the following specific steps:
In this embodiment, receiving human body posture data includes: receiving angle data of front legs and rear legs of a human body, receiving angle data of arms and a body main body of the human body, and receiving angle data of the arms and the head of the human body.
And 606, summing and averaging the obtained products, and finishing scoring on the human body posture data by combining the audio and video scoring parameters.
The scoring method for the human body posture disclosed by the embodiment of the disclosure receives human body posture data; analyzing and reading the audio and video scoring parameters; and scoring the human body posture data according to the audio and video scoring parameters. According to the method, the beneficial effect of accurate scoring in the human-computer interaction virtual enhanced display state is achieved by receiving and analyzing the human body posture data and reading the audio and video scoring parameters, and meanwhile, the strong interactivity and the experience of the human-computer interaction are achieved.
In the embodiment, the sound characteristics and the action characteristics of the standard audio and video are preset in the acquisition application program, so that the analysis and reading of the audio and video scoring parameters are more detailed and multidimensional, and a data base is laid for the accuracy of scoring the human body posture data according to the audio and video scoring parameters.
Fig. 8 is a hardware block diagram illustrating a scoring apparatus of a human body posture according to an embodiment of the present disclosure. As shown in fig. 8, the scoring device 80 for human body posture according to the embodiment of the present disclosure includes a memory 801 and a processor 802. The various components of the body pose scoring apparatus 80 are interconnected by a bus system and/or other form of connection mechanism (not shown).
The memory 801 is used to store non-transitory computer readable instructions. In particular, memory 801 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory can include, for example, Random Access Memory (RAM), cache memory (or the like). The non-volatile memory may include, for example, Read Only Memory (ROM), a hard disk, flash memory, and the like.
The processor 802 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the body gesture scoring apparatus 80 to perform desired functions. In an embodiment of the present disclosure, the processor 802 is configured to execute the computer readable instructions stored in the memory 801, so that the human body posture scoring device 80 executes the above human body posture scoring method. The human body posture scoring device is the same as the above-described embodiment of the human body posture scoring method, and a repeated description thereof will be omitted herein.
Fig. 9 is a schematic diagram illustrating a computer-readable storage medium according to an embodiment of the present disclosure. As shown in fig. 9, a computer-readable storage medium 900 according to embodiments of the present disclosure has non-transitory computer-readable instructions 901 stored thereon. The non-transitory computer readable instructions 901, when executed by a processor, perform the method of scoring a human pose according to embodiments of the present disclosure described above with reference to the above.
In the above, a human body posture scoring method and device, and a computer-readable storage medium according to the embodiments of the present disclosure. By receiving and analyzing the human body posture data and reading the audio and video scoring parameters, the beneficial effect of scoring accuracy in the human-computer interaction virtual enhanced display state is achieved, and meanwhile, the strong interactivity and the experience of the human-computer interaction are achieved.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
Also, as used herein, "or" as used in a list of items beginning with "at least one" indicates a separate list, such that, for example, a list of "A, B or at least one of C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the described example is preferred or better than other examples.
It is also noted that in the systems and methods of the present disclosure, components or steps may be decomposed and/or re-combined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
Various changes, substitutions and alterations to the techniques described herein may be made without departing from the techniques of the teachings as defined by the appended claims. Moreover, the scope of the claims of the present disclosure is not limited to the particular aspects of the process, machine, manufacture, composition of matter, means, methods and acts described above. Processes, machines, manufacture, compositions of matter, means, methods, or acts, presently existing or later to be developed that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein may be utilized. Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or acts.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (16)
1. A scoring method for human body postures is characterized by comprising the following steps:
receiving human body posture data;
analyzing and reading the audio and video scoring parameters;
grading the human body posture data according to the audio and video grading parameters; wherein, the scoring the human body posture data according to the audio and video scoring parameters comprises: obtaining a product of an action characteristic matrix and a transposed matrix of the action characteristic matrix, taking the product as a first matrix, and summing the first matrix and an adjustment unit matrix to obtain a second matrix; wherein the adjustment unit matrix is the product of the unit matrix and an adjustment coefficient, and the adjustment coefficient is a constant greater than 0; obtaining the product of the inverse matrix of the second matrix, the action characteristic matrix and the transposed matrix of the scoring matrix as a scoring matrix in the action characteristic space; the scoring matrix is related to the audio and video scoring parameters, the action characteristic matrix is related to the human body posture data, and a virtual enhanced display technology is adopted for an application program which analyzes and reads the audio and video scoring parameters; the scoring matrix is formed by analyzing the bone node information and the bone node information of at least one human-computer interaction action of the human-computer interaction actions with different grades of difficulty and the matching ratio of the bone node information and the music rhythm, calculating the bone node information and the music rhythm to obtain the score of the human-computer interaction action with a certain grade and scoring the human-computer interaction actions with different grades of difficulty.
2. A scoring method for human body gestures according to claim 1, wherein said receiving human body gesture data comprises: receiving angle data of front legs and rear legs of a human body, receiving angle data of arms and a body main body of the human body, and receiving angle data of the arms and the head of the human body.
3. A scoring method for human body posture according to claim 2, characterized by further comprising: and carrying out weight assignment on the received multiple groups of human body posture data, assigning a first weight value to the human body front leg and back leg angle data, assigning a second weight value to the human body arm and body main body angle data, and assigning a third weight value to the human body arm and head angle data.
4. The human body posture scoring method according to claim 1, wherein the analyzing and reading audio and video scoring parameters comprises: and acquiring sound characteristics and action characteristics of a preset standard audio and video in an application program.
5. The human body posture scoring method according to claim 4, wherein the sound features of the preset standard audio-video comprise: loudness, pitch, timbre and tempo; the action features include: the action completion value, the action completion and audio and video rhythm matching ratio attribute value and the action completion time value.
6. A scoring method for human body gestures according to claim 3, further comprising: and respectively multiplying the first weight value, the second weight value and the third weight value by a preset standard template weight value to obtain a first product, a second product and a third product.
7. A scoring method for human body gestures according to claim 6, further comprising: respectively multiplying the first product, the second product and the third product by the depth values of the front legs and the rear legs of the human body, the depth values of the arms and the body main body of the human body and the depth values of the arms and the head angles of the human body;
and summing and averaging the obtained products, and finishing scoring on the human body posture data by combining the audio and video scoring parameters.
8. A 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.
9. A computer 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 of any of claims 1-7 are implemented when the program is executed by the processor.
10. A human posture scoring device, comprising:
the receiving module is used for receiving human body posture data;
the analysis and reading module is used for analyzing and reading the audio and video scoring parameters;
the scoring module is used for scoring the human body posture data according to the audio and video scoring parameters;
wherein, the scoring the human body posture data according to the audio and video scoring parameters comprises: obtaining a product of an action characteristic matrix and a transposed matrix of the action characteristic matrix, taking the product as a first matrix, and summing the first matrix and an adjustment unit matrix to obtain a second matrix; wherein the adjustment unit matrix is the product of the unit matrix and an adjustment coefficient, and the adjustment coefficient is a constant greater than 0; obtaining the product of the inverse matrix of the second matrix, the action characteristic matrix and the transposed matrix of the scoring matrix as a scoring matrix in the action characteristic space; the scoring matrix is related to the audio and video scoring parameters, the action characteristic matrix is related to the human body posture data, and the analysis and reading module adopts a virtual enhancement display technology to the application program for analyzing and reading the audio and video scoring parameters; the scoring matrix is formed by analyzing the bone node information and the bone node information of at least one human-computer interaction action of the human-computer interaction actions with different grades of difficulty and the matching ratio of the bone node information and the music rhythm, calculating the bone node information and the music rhythm to obtain the score of the human-computer interaction action with a certain grade and scoring the human-computer interaction actions with different grades of difficulty.
11. The device for scoring of human body posture of claim 10, wherein the receiving module is further configured to receive human body front leg and back leg angle data, human body arm and body angle data, and human body arm and head angle data.
12. A scoring device for human body posture as claimed in claim 11, further comprising: and the weight assignment module is used for carrying out weight assignment on the plurality of groups of acquired human posture data, assigning a first weight value to the angle data of the front legs and the rear legs of the human body, assigning a second weight value to the angle data of the arms and the body main body of the human body, and assigning a third weight value to the angle data of the arms and the head of the human body.
13. The human body posture scoring device according to claim 10, wherein the parsing and reading module comprises: and the acquisition unit is used for acquiring the sound characteristics and the action characteristics of the preset standard audio and video in the application program.
14. The human body posture scoring device according to claim 13, wherein the sound features of the preset standard audio-video comprise: loudness, pitch, timbre and tempo; the action features include: the action completion value, the action completion and audio and video rhythm matching ratio attribute value and the action completion time value.
15. A scoring device for human body posture as claimed in claim 12, further comprising: and the first calculation module is used for respectively multiplying the first weight value, the second weight value and the third weight value by a preset standard template weight value to obtain a first product, a second product and a third product.
16. A scoring device for human body posture as claimed in claim 15, further comprising: the second calculation module is used for respectively multiplying the first product, the second product and the third product by the depth values of the front legs and the rear legs of the human body, the depth values of the arms of the human body and the body main body of the human body and the depth values of the arms of the human body and the angle of the head of the human body;
and the third calculation module is used for summing and averaging the obtained products and finishing the scoring of the human body attitude data by combining the audio and video scoring parameters.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810273540 | 2018-03-29 | ||
| CN2018102735405 | 2018-03-29 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108509924A CN108509924A (en) | 2018-09-07 |
| CN108509924B true CN108509924B (en) | 2020-01-14 |
Family
ID=63380852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810301255.XA Active CN108509924B (en) | 2018-03-29 | 2018-04-04 | Human body posture scoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108509924B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020630B (en) * | 2019-04-11 | 2020-12-18 | 成都乐动信息技术有限公司 | Method and device for evaluating action completion degree, storage medium and electronic equipment |
| CN113255462A (en) * | 2021-04-29 | 2021-08-13 | 深圳大学 | Gait scoring method, system, computer program product and readable storage medium |
| CN114429647A (en) * | 2022-01-21 | 2022-05-03 | 上海浦东发展银行股份有限公司 | Progressive character interaction identification method and system |
| CN114440884A (en) * | 2022-04-11 | 2022-05-06 | 天津果实科技有限公司 | Intelligent analysis method for human body posture for intelligent posture correction equipment |
| CN118193988B (en) * | 2024-05-13 | 2024-09-06 | 首都体育学院 | Music expressive force evaluation method for actions in pattern skating |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106075854A (en) * | 2016-07-13 | 2016-11-09 | 牡丹江师范学院 | A kind of dance training system |
| CN107122048A (en) * | 2017-04-21 | 2017-09-01 | 甘肃省歌舞剧院有限责任公司 | One kind action assessment system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106448279A (en) * | 2016-10-27 | 2017-02-22 | 重庆淘亿科技有限公司 | Interactive experience method and system for dance teaching |
-
2018
- 2018-04-04 CN CN201810301255.XA patent/CN108509924B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106075854A (en) * | 2016-07-13 | 2016-11-09 | 牡丹江师范学院 | A kind of dance training system |
| CN107122048A (en) * | 2017-04-21 | 2017-09-01 | 甘肃省歌舞剧院有限责任公司 | One kind action assessment system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108509924A (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509924B (en) | Human body posture scoring method and device | |
| CN108615055B (en) | Similarity calculation method and device and computer readable storage medium | |
| JP7337104B2 (en) | Model animation multi-plane interaction method, apparatus, device and storage medium by augmented reality | |
| US11721114B2 (en) | Method, system, and device of generating a reduced-size volumetric dataset | |
| Zurdo et al. | Animating wrinkles by example on non-skinned cloth | |
| CN109144252B (en) | Object determination method, device, equipment and storage medium | |
| CN109308437B (en) | Motion recognition error correction method, electronic device, and storage medium | |
| US20110306468A1 (en) | Caloric burn determination from body movement | |
| JP2019096113A (en) | Processing device, method and program relating to keypoint data | |
| CN104966284A (en) | Method and equipment for acquiring object dimension information based on depth data | |
| US20200334862A1 (en) | Moving image generation apparatus, moving image generation method, and non-transitory recording medium | |
| Aditya et al. | Recent trends in HCI: A survey on data glove, LEAP motion and microsoft kinect | |
| WO2019184633A1 (en) | Human-machine interaction system, method, computer readable storage medium, and interaction device | |
| WO2024213025A1 (en) | Hand modeling method, hand model processing method, device, and medium | |
| CN111882380A (en) | Virtual fitting method, device, system and electronic equipment | |
| CN111160308B (en) | Gesture recognition method, device, equipment and readable storage medium | |
| CN113743237A (en) | Follow-up action accuracy determination method and device, electronic device and storage medium | |
| CN111353347B (en) | Action recognition error correction method, electronic device, and storage medium | |
| CN108549484A (en) | Man-machine interaction method and device based on human body dynamic posture | |
| CN111353345B (en) | Method, apparatus, system, electronic device, and storage medium for providing training feedback | |
| CN108629824B (en) | Image generation method and device, electronic equipment and computer readable medium | |
| Liu et al. | COMTIS: Customizable touchless interaction system for large screen visualization | |
| CN115239856A (en) | Animation generation method and device for 3D virtual object, terminal device and medium | |
| CN114299615A (en) | Key point-based multi-feature fusion action identification method, device, medium and equipment | |
| CN108519823B (en) | Terminal-based human-computer interaction data processing method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230103 Address after: Room 1445A, No. 55 Xili Road, China (Shanghai) Pilot Free Trade Zone, Pudong New Area, Shanghai, 200120 Patentee after: Honey Grapefruit Network Technology (Shanghai) Co.,Ltd. Address before: 100080 408, 4th floor, 51 Zhichun Road, Haidian District, Beijing Patentee before: BEIJING MICROLIVE VISION TECHNOLOGY Co.,Ltd. |