WO2017161734A1

WO2017161734A1 - Correction of human body movements via television and motion-sensing accessory and system

Info

Publication number: WO2017161734A1
Application number: PCT/CN2016/088197
Authority: WO
Inventors: 李水旺
Original assignee: 乐视控股（北京）有限公司; 乐视致新电子科技（天津）有限公司
Priority date: 2016-03-24
Filing date: 2016-07-01
Publication date: 2017-09-28
Also published as: CN105847987A

Abstract

Embodiments of the present application are applicable in the technical field of motion sensing. Provided are a method and system for correcting human body movements via a television and a motion-sensing accessory. The method comprises: a motion-sensing accessory recognizes a human body movement in a current frame of image and acquires a simulated action corresponding to the human body movement; the motion-sensing accessory compares the acquired simulated action with a preset action sample and determines the difference between the simulated action and the action sample; and the motion-sensing accessory generates correction tip information on the basis of the determined difference and plays back the correction tip information via a television. The embodiments of the present application are capable of automatically monitoring human body movements and providing correction tips.

Description

Correcting human movements and systems with TV and somatosensory accessories

This application claims priority to Chinese Patent Application No. 201610173854.9, filed on March 24, 2016, entitled "Correcting Human Body Actions and Systems Through Television and Somatosensory Accessories", the entire contents of which are incorporated by reference. In this application.

Technical field

The embodiments of the present application relate to the field of somatosensory recognition technologies, and in particular, to a human body motion and system through a television and a somatosensory accessory.

Background technique

As the quality of life continues to increase, people are under increasing pressure to live. In order to relieve stress, maintain good health or shape a better body, people often choose to perform a variety of sports, such as running, doing yoga or doing aerobics.

Due to the increasing environmental problems, outdoor air quality tends to be poor, so people are more willing to choose to engage in sports indoors. For example, people can go to the gym, engage in sports such as running, yoga, swimming, etc., or they can follow the fitness exercises in the TV at home.

At present, if you choose to go to the gym for exercise, then the price of the gym is often higher, which will increase the daily expenses of the exerciser; on the other hand, the number of coaches in the gym is often limited, it is impossible to develop a suitable exercise plan for each exerciser or Guide the movements. If you choose to follow the fitness exercises in the TV at home to exercise, then the exercisers often can not observe their own sports, sometimes the action is not in place will greatly reduce the efficiency of fitness.

In view of the above situation, the exerciser can place a floor mirror beside the TV, so that he can see whether his or her movement is normal when he follows the action in the TV. In the process of implementing the present application, the inventors have found that such a method is too complicated and takes up space in the room, so that the exerciser cannot exercise in a stretch. At the same time, the exerciser needs to take into account both the standard movements in the TV set and the movements in the floor mirror, which will make the exerciser more tired, and through the contrast of the naked eye, it is impossible to keep the movements and the standard movements completely consistent.

It can be seen from the above that there is a need in the prior art for a method of correcting human motion.

Summary of the invention

Embodiments of the present application provide a method for correcting human body motion through a television and a somatosensory accessory And the system can automatically monitor the movement of the human body and correct the movement of the human body.

An embodiment of the present application provides a method for correcting a human body motion through a television and a somatosensory accessory. The television and the body-sensing accessory are communicatively coupled. The method includes: the somatosensory accessory identifies a human body motion in a current frame image, and acquires the human body motion. a motion corresponding to the motion; the somatosensory accessory compares the acquired simulated motion with a preset motion specimen to determine a difference between the simulated motion and the motion specimen; the somatosensory accessory generates a correction according to the determined difference Prompt information and play the correction prompt information on the TV.

Further, the simulation action includes a human skeleton corresponding to the human body motion; the human body motion in the current frame image is recognized, and a simulation action corresponding to the human body motion is acquired, including: using a preset The body part classifier identifies a preset number of target parts corresponding to the human body motion in the current frame picture; performs clustering processing on the pixel points in the preset number of target parts identified according to a preset clustering algorithm, and acquires each a bone point corresponding to the target part; the acquired bone point constitutes a simulated motion corresponding to the human body motion.

Further, the using the preset body part classifier to identify a preset number of target parts corresponding to the human body motion in the current frame picture comprises: acquiring a body part training set, wherein the body part training set includes a preset number of human bodies a part sample map; extracting a feature value vector of the body part sample map of the human body part training; calculating a classification condition of the body part training part sample map according to the extracted feature value vector; based on the classification condition Identifying a preset number of target parts corresponding to human motion in the current frame picture.

Further, comparing the acquired simulated action with a preset motion sample, determining a difference between the simulated motion and the motion specimen, including: acquiring a center point of the simulated motion and a preset The center points of the set motion specimens coincide; the difference between the simulated motion and the motion specimen at the preset position is determined.

Further, the correction prompt information played by the television is voice information or text information or image information.

Further, the method further includes: identifying a preset object in the current frame picture, and calculating a motion amount corresponding to the human body in the current frame picture according to the number of times of reciprocation of the preset object in the preset area.

An embodiment of the present application provides a computer readable recording medium having recorded thereon a program configured to execute the above method.

Embodiments of the present application provide a system for correcting a human body motion through a television and a somatosensory accessory, the system comprising: a somatosensory accessory configured to recognize a human body motion in a current frame image, and obtain a simulated motion corresponding to the human body motion And comparing the obtained simulated motion with the preset motion specimen, determining a difference between the simulated motion and the motion specimen; generating corrective prompt information according to the determined difference; the television, and the somatosensory accessory The communication connection is configured to display an action specimen preset by the somatosensory accessory, and play the correction prompt information generated by the somatosensory accessory.

Further, the simulation action includes a human skeleton corresponding to the human body motion; the somatosensory accessory identifies a human body motion in a current frame image, and acquires a simulation motion corresponding to the human body motion, specifically: The somatosensory accessory uses a pre-set body part classifier to identify a preset number of target parts corresponding to the human body motion in the current frame picture; and perform pixel points in the preset number of target parts identified according to a preset clustering algorithm The clustering process acquires a skeletal point corresponding to each target part; and the acquired skeletal point constitutes a simulated action corresponding to the human body motion.

Further, the somatosensory accessory uses a pre-set body part classifier to identify a preset number of target parts corresponding to the human body motion in the current frame picture, specifically: the somatosensory accessory acquires a human body part training set, and the body part training Concentrating includes a preset number of human body part sample maps; extracting a feature value vector of the human body part training concentrated human body part sample map; calculating a classification condition of the human body part training concentrated human body part sample map based on the extracted feature value vector And identifying, according to the classification condition, a preset number of target parts corresponding to the human body motion in the current frame picture.

Further, the somatosensory accessory is further configured to: identify a preset object in the current frame picture, and calculate a corresponding body in the current frame picture according to a number of times of reciprocation of the preset object in a preset area The amount of exercise.

The method and system for correcting human body motion through a television and a somatosensory accessory are provided by the embodiments of the present application, and the human body motion is monitored by using the somatosensory accessory, and the human body motion in the current frame picture is recognized, so that the human body motion can be acquired. Corresponding simulation action; Comparing the acquired simulation action with the standard action in the television, it is possible to know whether the human body action is standardized, and when it is not standardized, the correction prompt information can be sent to the exerciser in front of the television. It can be seen from the above that the embodiment of the present application realizes automatic monitoring of human body motion and selectively corrects the prompt.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments or the description of the prior art will be briefly introduced one by one. It is obvious that the drawings in the following description are Some embodiments of the present application can also obtain other drawings based on these drawings without any creative work for those skilled in the art.

1 is a flow chart of a method for correcting a human body motion through a television and a somatosensory accessory according to an embodiment of the present application;

FIG. 2 is a flowchart of a method for identifying a human skeleton corresponding to a human body motion in a current frame picture according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of calculating a classification condition by a support vector machine according to an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present application. It is a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without the inventive work are all within the scope of the present application.

Although the processes described below include a plurality of operations occurring in a particular order, it should be clearly understood that the processes can include more or fewer operations that can be performed sequentially or in parallel, such as using a parallel processor or a multi-threaded environment.

FIG. 1 is a flow chart of a method for correcting a human body motion through a television and a somatosensory accessory according to an embodiment of the present application. As shown in FIG. 1, the method includes:

Step S1: The somatosensory accessory recognizes the human body motion in the current frame picture, and acquires a simulated motion corresponding to the human body motion.

In the embodiment of the present application, the body motion of the front exerciser of the television can be monitored by installing the somatosensory accessory on the television, wherein the somatosensory accessory can be a somatosensory camera.

In the embodiment of the present application, the somatosensory accessory can identify the human body motion in the current frame picture to obtain a simulated motion corresponding to the human body motion. In the embodiment of the present application, the process of recognizing the human body motion may be performed in the somatosensory accessory or in a processor connected to the somatosensory accessory. For example, after acquiring the current frame picture, the somatosensory accessory can send the picture to a processor connected thereto, and then the current frame picture can be identified by the processor.

In the embodiment of the present application, the simulated action may be an action that is completely consistent with the action of the human body, or may be only a human bone corresponding to the action of the human body. In the embodiment of the present application, considering that the human body can be represented by 20 skeletal points, the human body skeleton corresponding to the human body motion can be generated after recognizing the human body motion in the current frame picture. Multiple bone points can be included in the bone, such as at least 20. The human bone can reflect the movements of various parts of the human body in front of the television, thereby facilitating comparison of the human body motion with the standard motion in the television.

In the embodiment of the present application, as shown in FIG. 2, the human skeleton corresponding to the human motion in the current frame picture may be specifically identified by the following steps.

Step S11: Identify a preset number of target parts corresponding to the human body motion in the current frame picture by using a preset body part classifier.

In the embodiment of the present application, a human body part classifier may be preset, and the human body part classifier may analyze a picture of the human body to identify various parts included in the human body. For example, the human body can be divided into a head, a shoulder, an arm, an elbow, a crotch, a foot, a wrist, a hand, a trunk, a leg, and a knee, and each of the above-mentioned parts can be further divided into Multiple sections up, down, left and right to allow for more precise identification of the human body.

In the embodiment of the present application, the human body part classifier can be established by a machine learning method, that is, the human body part classifier is trained by using pictures of various parts of the human body, so that the human body part classifier can be generated. To divide the classification conditions of different parts, and then input the picture to be processed to the body part classifier, so that The classification condition identifies each human body part in the picture to be processed.

Specifically, in the embodiment of the present application, the human body part training set may be acquired in advance, and the human body part training set includes a preset number of human body part sample maps. In order to ensure that the obtained classification conditions are relatively accurate, in the embodiment of the present application, as many human body part sample maps as possible can be set in the human body part training set, and the human body part sample map can cover the above various human body parts. After acquiring the training set of the human body part, in the embodiment of the present application, the feature value vector of the sample map of the human body part in the training part of the human body part may be extracted. The feature value vector may be a pixel value vector corresponding to the body part sample map. Since the body part sample map is composed of a plurality of pixel points, in the embodiment of the present application, the RGB values corresponding to the respective pixel points may be extracted, and the feature values extracted by each pixel point are sequentially arranged to constitute the feature. Value vector. For example, the eigenvalue vector formed after the alignment is a series of arranged values in the form of:

(RGB(1,1), RGB(1,2),...,RGB(1,120),RGB(2,1),RGB(2,2),...,RGB(2,120),...,RGB(200,1 ), RGB (200, 2), ... RGB (200, 120))

Where RGB(m,n)=Ra, Gb, Bc,m,n respectively represent the row and column of a pixel in the sample image of the human body part; for the picture of 200 pixels*120 pixels, the value of m The range can be from 1 to 200, and the value of n can range from 1 to 120. Ra, Gb, Bc are any integers from 0 to 255 to represent the RGB values corresponding to the pixel points, respectively.

In the embodiment of the present application, after extracting the feature value vector corresponding to each human body part sample map, the classification condition of the human body part training concentrated body part sample map may be calculated based on the extracted feature value vector. Specifically, an implementation method of calculating a classification condition of a body part sample map in the training sample is introduced by using a support vector machine (Support Vector Machine) algorithm as an example. Support vector machines were first proposed by Cortes and Vapnik in 1995. They show many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition, and can be applied to other machine learning problems such as function fitting. Overall, support vector machines can solve the problem of classification and classification criteria for complex transactions.

The basic principle of classification by the support vector machine algorithm is explained using the example of the linear classification shown in FIG. As shown in FIG. 3, the points in the left graph represent the input training samples, and the points represented by the forks in the right graph represent the calculated C1 training samples, and the points represented by the circles. Indicates the calculated C2 training sample. As shown in FIG. 3, after the training samples are calculated by the support vector machine algorithm, the classified training samples C1 and C2 can be obtained, and the classification conditions of the C1 and C2 classes can be obtained.

For the linear classification of Figure 3, the categorization condition (vv' line in the figure, also known as hyperplane) can be represented by a linear function, for example as:

f(x)=wx+b

Where w and b are parameters obtained by the support vector machine to calculate the eigenvalue vector set (called "training" in the support vector machine), and x represents the eigenvalue vector of the picture.

f(x) represents the mapping relationship in the support vector machine. For the case of f(x) = 0, the eigenvalue vector x at this time is located on the hyperplane. For the case where f(x) is greater than 0, the eigenvalue vector corresponding to the upper right side of the hyperplane in the graph on the right side of FIG. 3; for the case where f(x) is less than 0, the eigenvalue corresponding to the lower left side of the hyperplane in the graph of the right side of FIG. vector.

The input feature value vectors are, for example, two-dimensional vectors, that is, corresponding to each point on the coordinates in FIG. The support vector machine algorithm, which continuously searches for the straight line within the range of the input feature value vector, obtains such a straight line by trying to calculate the distance between each searched line and each feature value vector (the point in the figure): The straight line is the largest and equal distance from the nearest feature value vector on both sides. As shown in the right graph of Fig. 3, the calculated straight line vv' is a hyperplane. It can be seen from the right graph in Fig. 3 that in the two-dimensional case, the hyperplane vv' is a straight line, and the straight line is the largest and equal distance from the nearest feature value vector on both sides, and the distance is L.

In this way, the classification condition of different human body parts in the training samples can be obtained by the algorithm of the support vector machine. Then, in the embodiment of the present application, a preset number of target parts corresponding to the human body motion in the current frame picture may be identified based on the categorization condition. Specifically, the human body part classifier may classify the human body motions in the current frame picture by using the classification condition, thereby identifying a preset number of target parts included in the human body motion in the current frame picture.

Step S12: Perform clustering processing on the pixel points in the preset target number of the identified target points according to the preset clustering algorithm, and acquire the skeletal points corresponding to each target part.

In the implementation manner of the present application, after acquiring a plurality of target parts corresponding to the human body motion in the current frame picture, the preset number of objects that are identified may be determined according to a preset clustering algorithm. The pixel points in the target part are clustered to obtain the bone points corresponding to each target part. Specifically, the clustering algorithm may include at least one of a K-MEANS algorithm, a cohesive hierarchical clustering algorithm, or a DBSCAN algorithm. The clustering algorithm can gather the pixel points in the identified target part to a point, and the final gathered point can be used as the skeletal point corresponding to the target part.

In this way, each identified target part is clustered, so that the skeletal points corresponding to the respective target parts can be obtained.

Step S13: The acquired skeleton points constitute a simulation action corresponding to the human body motion.

In the embodiment of the present application, after the skeleton points corresponding to the respective target portions are acquired, the skeleton points are sequentially connected, and a skeleton map corresponding to the human body motion can be obtained, and the skeleton map can be used as Get the simulated action.

In the simulation action, the connection between two adjacent bone points can form a human body motion, for example, the line between the left shoulder bone point and the left elbow bone point can outline the left upper arm line of the human body. The outlined line can be used as a simulation action corresponding to the left upper arm of the human body motion.

Step S2: comparing the obtained simulated motion with a preset motion specimen to determine a difference between the simulated motion and the motion specimen.

In the embodiment of the present application, after the simulated action corresponding to the human body motion is acquired, the acquired simulated motion may be compared with the preset motion specimen to determine whether the current human motion and the motion specimen are consistent, That is to say, by comparing the simulated action with the action specimen, it can be determined whether the human body motion is in place at the current moment.

In the embodiment of the present application, the center point of the simulated motion to be acquired may be coincident with the center point of the preset motion specimen. The center point may be the center point of the human torso, such as the center point of the chest cavity. After the center point of the simulated motion is coincident with the center point of the preset motion specimen, it can be determined whether the other portion of the simulated motion corresponds to the other portion of the motion specimen. In this way, the difference between the simulated motion and the motion specimen at the preset position can be determined.

In the embodiment of the present application, the preset position may be preset for different action specimens. Specify first. For example, for an action specimen, the focus is on the accuracy of the position of the arms and feet. Then, in this case, the arm and the foot in the action specimen can be determined as the preset position, and when the simulated motion and the motion specimen are compared, only the positions of the arm and the foot can be compared, thereby determining The difference between the simulated motion and the motion specimen at the position of the arm and the foot.

Step S3: Generate corrective prompt information according to the determined difference, and play the corrected prompt information by using a television, and the corrected prompt information is voice information or text information or image information.

In the embodiment of the present application, when there is a difference between the simulated action and the action specimen at the preset position, the correction prompt information may be generated according to the determined difference. The correction prompt information may correspond to the preset position in step S2. For example, when there is a difference between the simulated motion and the motion specimen at the position of the arm, the correction prompt information of "arm position mismatch" can be generated.

Further, in the embodiment of the present application, it is also possible to generate more specific correction prompt information. For example, when it is determined that there is a difference between the simulated action and the preset position of the motion specimen, the positional relationship between the simulated motion and the motion specimen at the preset position may be further determined, and a more detailed correction is generated based on the determined positional relationship. Prompt message. For example, when the simulated motion is inconsistent with the arm portion in the motion specimen, the positional relationship between the arm of the simulated motion and the arm of the motion specimen can be determined. For example, the arm of the simulated motion is located above the arm of the motion specimen, then In this case, a correction message "Please move the arm down" can be generated to more clearly remind the exerciser of the area to be corrected and the direction of correction.

In another embodiment of the present application, in addition to correcting the movement of the human body, the exercise amount of the exerciser may be counted according to the difference of the exercise equipment used by the exerciser. Specifically, in the embodiment of the present application, the preset object in the current frame picture may be identified. The preset object may be, for example, an exercise device such as a dumbbell or a barbell. The specific recognition process can also be performed by the support vector machine method, by learning different exercise devices to generate classification conditions for classifying different exercise devices, and further, the classification conditions can be used in the current frame picture. Exercise equipment for identification.

After the preset object in the current frame picture is identified, the amount of motion corresponding to the human body in the current frame picture may be calculated according to the number of times of reciprocation of the preset object in the preset area. The preset area may be determined in advance according to the difference of the preset object, and the preset area may be a range of positions where the preset object is used by the exerciser. For example, the preset area of the dumbbell is often the length range of the exerciser's arm, and the preset area of the barbell may be the length range of the exerciser's height. In the embodiment of the present application, the preset object performs a reciprocating motion in the preset area, and then the exerciser can be considered to perform one motion, so that the number of reciprocations of the preset object in the preset area can be counted. Calculate the amount of exercise of the exerciser.

As can be seen from the above, the embodiment of the present application provides a method for correcting a human body motion through a television and a somatosensory accessory, and monitoring the human body motion using the somatosensory accessory, and recognizing the human body motion in the current frame image, thereby obtaining the action with the human body. Corresponding simulation action; by comparing the acquired simulation action with the standard action in the television, it can be known whether the human body action is standardized, and when it is not standardized, the correction prompt information can be sent to the exerciser in front of the TV.

The computer readable recording medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer). For example, a machine-readable medium includes read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , infrared signals, digital signals, etc.).

Embodiments of the present application also provide a system for correcting human body motion through a television and a somatosensory accessory. The system can include:

The somatosensory accessory is configured to identify a human body motion in the current frame image, obtain a simulated motion corresponding to the human body motion, compare the acquired simulated motion with a preset motion specimen, and determine the simulated motion and the simulated motion a difference between the action specimens; generating correction prompt information according to the determined difference;

The television is communicatively connected to the somatosensory accessory, configured to display an action specimen preset by the somatosensory accessory, and play the correction prompt information generated by the somatosensory accessory, wherein the correction prompt information is voice Information or text information or image information.

In a specific embodiment of the present application, the somatosensory accessory may be a somatosensory camera.

In a specific embodiment of the present application, the simulated action includes a human skeleton corresponding to the human body motion.

Correspondingly, the somatosensory accessory recognizes the human body motion in the current frame picture, and acquires a simulation action corresponding to the human body motion, specifically:

The somatosensory accessory uses a pre-set body part classifier to identify a preset number of target parts corresponding to the human body motion in the current frame picture; and the pixel points in the preset number of target parts identified according to a preset clustering algorithm Performing a clustering process to acquire a skeletal point corresponding to each target part; and the acquired skeletal point constitutes a simulated action corresponding to the human body action.

The somatosensory accessory uses a pre-set body part classifier to identify a preset number of target parts corresponding to the human body motion in the current frame picture, specifically: the somatosensory accessory acquires a human body part training set, and the human body part training set Include a preset number of human body part sample maps; extract a feature value vector of the human body part training concentrated human body part sample map; calculate a classification condition of the human body part training concentrated human body part sample map based on the extracted feature value vector; And determining, according to the classification condition, a preset number of target parts corresponding to the human body motion in the current frame picture.

The somatosensory accessory compares the acquired simulated motion with a preset motion specimen to determine a difference between the simulated motion and the motion specimen, specifically: the simulated motion that the somatosensory accessory will acquire The center point coincides with a center point of the preset motion specimen; and the difference between the simulation motion and the motion specimen at the preset position is determined.

In another embodiment of the present application, the somatosensory accessory is further configured to identify a preset object in the current frame picture, and calculate a number of times of reciprocation in the preset area according to the preset object. The amount of motion corresponding to the human body in the current frame picture.

It should be noted that the specific implementation manners of the foregoing various functional modules are consistent with the descriptions in the foregoing steps S1 to S3 in the method for correcting human body motion through the television and the somatosensory accessory, and are not described herein again.

Those skilled in the art can understand that all or part of the steps in implementing the above embodiments may be completed by a program instructing related hardware, and the program is stored in a storage medium. A number of instructions are included to cause a device (which may be a microcontroller, chip, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

It can be seen from the above that the method and system for correcting human body motion through the television and the somatosensory accessory are provided by the embodiment of the present application, and the human body motion is monitored by using the somatosensory accessory, and the human body motion in the current frame picture is recognized, thereby obtaining and The simulation action corresponding to the human body motion; by comparing the acquired simulation action with the standard action in the television, it is possible to know whether the human body action is standardized, and when it is not standardized, it can issue a correction to the exerciser in front of the TV set. Prompt message.

The above description of various embodiments of the present application is provided to those skilled in the art for the purpose of description. It is not intended to be exhaustive or to limit the invention to the single disclosed embodiments. As described above, various alternatives and variations of the present application will be apparent to those skilled in the art. Thus, while a few alternative embodiments have been discussed in detail, other embodiments will be apparent or apparent to those skilled in the art. The present application is intended to cover all alternatives, modifications, and variations of the present invention, as well as other embodiments that fall within the spirit and scope of the application.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the method embodiment, since it is basically similar to the system embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the system embodiment.

While the present invention has been described by the embodiments of the present invention, it will be understood by those skilled in the art

Claims

A method for correcting a human body motion through a television and a somatosensory accessory, wherein the television and the somatosensory accessory are communicatively coupled, wherein the method comprises:

The somatosensory accessory recognizes the human body motion in the current frame picture, and acquires a simulated motion corresponding to the human body motion;

The somatosensory accessory compares the acquired simulated motion with a preset motion specimen to determine a difference between the simulated motion and the motion specimen;

The somatosensory accessory generates correction prompt information according to the determined difference, and plays the correction prompt information through a television.
The method of correcting a human body motion by a television and a somatosensory accessory according to claim 1, wherein the simulated motion comprises a human skeleton corresponding to the human body motion;

The identifying the human motion in the current frame image, and acquiring the simulated motion corresponding to the human motion, including:

Identifying a preset number of target parts corresponding to the human body motion in the current frame picture by using a preset body part classifier;

Performing clustering processing on the pixels in the preset number of target parts that are identified according to a preset clustering algorithm, and acquiring bone points corresponding to each target part;

The acquired bone points constitute a simulated motion corresponding to the human body motion.
The method for correcting a human body motion by using a television and a somatosensory accessory according to claim 2, wherein the pre-set body part classifier identifies a preset number of target parts corresponding to the human body motion in the current frame picture, including :

Obtaining a body part training set, wherein the body part training set includes a preset number of body parts sample maps;

Extracting a feature value vector of the sample map of the body part of the human body part training;

Calculating a classification condition of the sample map of the human body part training body set based on the extracted feature value vector;

And determining, according to the classification condition, a preset number of target parts corresponding to the human body motion in the current frame picture.
A method of correcting a human body motion by a television and a somatosensory accessory according to claim 1, The method is characterized in that: comparing the acquired simulated action with a preset action sample, determining a difference between the simulated action and the action specimen, including:

The center point of the acquired simulated motion is coincident with the center point of the preset motion specimen;

Determining the difference between the simulated motion and the motion specimen at a preset position.
The method for correcting a human body motion by a television and a somatosensory accessory according to claim 1, wherein the correction prompt information played by the television is voice information or text information or image information.
The method of claim 1, wherein the method further comprises:

Identifying a preset object in the current frame picture, and calculating a motion amount corresponding to the human body in the current frame picture according to the number of times of reciprocation of the preset object in the preset area.
A system for correcting human motion through a television and a somatosensory accessory, the system comprising:

The somatosensory accessory is configured to identify a human body motion in the current frame image, obtain a simulated motion corresponding to the human body motion, compare the acquired simulated motion with a preset motion specimen, and determine the simulated motion and the simulated motion a difference between the action specimens; generating correction prompt information according to the determined difference;

The television is communicably connected to the somatosensory accessory, configured to display an action specimen preset by the somatosensory accessory, and play the correction prompt information generated by the somatosensory accessory.
The system for correcting a human body motion by a television and a somatosensory accessory according to claim 7, wherein the simulated motion comprises a human skeleton corresponding to the human body motion;

The somatosensory accessory identifies the human body motion in the current frame picture, and acquires a simulated action corresponding to the human body motion, specifically:

The somatosensory accessory uses a pre-set body part classifier to identify a preset number of target parts corresponding to the human body motion in the current frame picture; and the pixel points in the preset number of target parts identified according to a preset clustering algorithm Performing a clustering process to acquire a skeletal point corresponding to each target part; and the acquired skeletal point constitutes a simulated action corresponding to the human body action.
The system for correcting a human body motion by a television and a somatosensory accessory according to claim 8, wherein the somatosensory accessory uses a preset body part classifier to identify the current The preset number of target parts corresponding to the human body motion in the frame picture is specifically:

The somatosensory accessory acquires a training set of a human body part, wherein the human body part training set includes a preset number of human body part sample maps; and extracting the feature value vector of the human body part training concentrated human body part sample map; and extracting the feature value vector based on Calculating a classification condition of the sample map of the body part in the training part of the human body part; and identifying a preset number of target parts corresponding to the human body motion in the current frame picture based on the classification condition.
The system for correcting a human body motion through a television and a somatosensory accessory according to claim 7, wherein the somatosensory accessory is further configured to:

Identifying a preset object in the current frame picture, and calculating a motion amount corresponding to the human body in the current frame picture according to the number of times of reciprocation of the preset object in the preset area.
A computer readable recording medium having recorded thereon a program configured to perform the method of claim 1.