KR20210053386A - Game Based Artificial Intelligence Fitness System and Method - Google Patents

Abstract

The present embodiments relate to a fitness assistance system for assisting fitness. Provided is a fitness assistance system including: a display unit that provides fitness-related fitness content to a target object using the fitness assistance system; an object recognition unit that detects the motion of the target object and collects motion information of the target object; and a processor that detects a motion characteristic according to the motion of the target object based on the motion information of the target object, compares the motion characteristic with a standard object, and controls an aspect in which fitness content is provided on the display unit.

Description

Game Based Artificial Intelligence Fitness System and Method

The present invention relates to a fitness assistance system and method, and more particularly, to a game-based artificial intelligence fitness assistance system for inducing continuous fitness motivation and interest of a user.

The content described in this section merely provides background information on the present embodiment and does not constitute the prior art.

The current fitness content has a high rate of giving up in the middle due to the absence of continuous interest and motivation. Interesting elements of game contents include a sense of victory through competition elements, cooperation through role elements, expectation through luck elements, and sense of accomplishment through goal elements. Give it.

In the field of smart fitness, image recognition technology based on artificial intelligence is one of the fields of technology research that is applied to user image processing and information processing. However, when recognizing an image, there are various obstacles and factors that interfere with recognition within the camera shooting range, and thus, there is a problem that the image recognition recognition rate is deteriorated. On the other hand, a technology that can improve the recognition rate of artificial intelligence-based image recognition technology is required, and as a method of improving the recognition rate, there are interlocking with Kinect and design of an optimal artificial intelligence model. However, in Kinect-based image recognition, there is a problem that it is impossible to identify and recognize factors that interfere with recognition.

Embodiments of the present invention propose a game-based artificial intelligence fitness exercise technology. The present invention can be applied in the field of smart fitness, and it is possible to induce a user's fitness through game content such as a fitness match between users, a character growth system, and a ranking system.

The present invention provides a personalized fitness program in consideration of personal characteristics such as the user's gender, age, body type, and exercise purpose, and provides continuous motivation through compensation for game character implementation according to fitness achievement level after fitness ends, The main purpose of the invention is to improve the recognition rate in the presence of factors that interfere with recognition through image recognition techniques based on artificial intelligence.

Other objects not specified of the present invention may be additionally considered within a range that can be easily deduced from the following detailed description and effects thereof.

In order to solve the above problem, a fitness assistance system according to an embodiment of the present invention, in a fitness assistance system for assisting fitness, transmits fitness content for fitness of a target object to the target object using the fitness assistance system. A display unit that provides, an object recognition unit that detects a motion of the target object and collects motion information of the target object, and a motion characteristic according to the motion of the target object are detected based on the motion information of the target object. And a processor that compares the motion characteristic and controls the manner in which the fitness content is provided to the display unit.

Here, the processor includes a game execution unit for executing interactive game content according to an operation of the target object and another target object connected through a network, and the display unit outputs a motion scene of the other target object.

Here, the object recognition unit includes a kinect configured to detect a motion of the target object to detect kinect information of the target object, and an image acquisition unit configured to detect a motion of the target object to collect image information of the target object, When the motion detection of the target object through the Kinect is not smooth, the image acquisition unit is used to prevent a reduction in recognition rate due to an obstruction factor.

Here, the processor controls a predetermined area of the display unit to form a predetermined brightness, and controls the display unit to provide fitness-related fitness content to the display unit, (i) body information on the target object, and (ii) A program selection unit for selecting a program of the fitness content based on the object information when at least one object information among) age, (iii) gender, (iv) body type, and (v) exercise purpose is input, and (i) the key Recognizing the target object based on the neck information to detect a motion characteristic according to the movement, or (ii) recognizing the target object by applying an input image of the target object to an image recognition model, and then using the image information And an image processing unit configured to detect motion characteristics according to the motion of the target object based on the target object.

Here, the program selection unit includes an information integration unit for integrating the object information on the input target object, an object information feature generation unit for generating an object information feature by extracting the integrated object information through a feature extraction algorithm, and the object And an object information feature classification unit for clustering information features and classifying the clustered object information features into a plurality of groups, and the program selection unit is a program of the fitness content suitable for the target object based on the classified plurality of groups I recommend.

Here, the image recognition model includes an outline extracting unit for extracting contour information of the target object, an contour merging unit for collecting body shape information of the target object by merging the contour information extracted from the contour extracting unit, and the target object. And a body feature extracting unit that determines each body structure of the target object based on the body shape information of, and recombines each body structure, and recognizes the target object based on the recombined body structure.

Here, the image processing unit labels the area of the target object based on the detected movement characteristic according to the movement of the target object, and the labeling moves according to the movement of the target object, and the movement characteristic of the standard object and the The matching rate is determined by comparing the labeling.

Here, the display unit is divided left and right to extract a movement image of the standard object and a movement image of the target object, and the display unit (i) the match rate, (ii) the number of movements of the target object, (iii) the target The target number of movements of the object and (iv) information on the amount of heat consumed by the target object are displayed at the top or bottom.

Here, when the matching rate of the target object falls below a preset value, the display unit displays a body organ of the target object whose matching rate is lower on the motion image of the target object, and a motion correction guidance image to increase the matching rate And the processor calculates a fitness achievement index of the target object based on the matching rate.

Here, the processor performs a character reinforcement that reinforces the character of the target object according to the achievement level using the fitness achievement index, and performs a ranking system that gives a ranking among the target objects based on the fitness achievement index. It is characterized by that.

In a fitness assistance method according to another embodiment of the present invention, in a fitness assistance method using a fitness assistance system for assisting fitness, fitness content related to fitness is provided to the target object using the fitness assistance system through a display unit. The step of detecting a motion of the target object and collecting motion information of the target object, and detecting a motion characteristic according to the motion of the target object based on the motion information of the target object, and comparing the motion characteristic of a standard object And controlling the manner in which the fitness content is provided to the display unit.

Here, the collecting motion information of the target object includes detecting the motion of the target object to detect the Kinect information of the target object, and collecting image information of the target object by detecting the motion of the target object. Including the step, wherein the step of collecting the image information of the target object is to prevent a reduction in recognition rate due to a factor that interferes when the motion detection of the target object is not smooth in the step of detecting the Kinect information of the target object. Carry out.

Here, the controlling of the manner in which the fitness content is provided to the display unit includes controlling a predetermined area of the display unit to form a predetermined brightness, and controlling the fitness content related to the fitness to be provided to the display unit, the At least one of (i) body information, (ii) age, (iii) gender, (iv) body type, and (v) exercise purpose for the target object is input, and the fitness content is displayed based on the object information. Selecting a program and (i) recognizing the target object based on the Kinect information to detect motion characteristics according to the movement of the target object, or (ii) image recognition of the input image for the target object And recognizing the target object by applying it to a model, and detecting a motion characteristic according to the movement of the target object based on the image information.

As described above, according to the embodiments of the present invention, the present invention can provide an effect of continuously inducing fitness use through content that induces interest in mobile game elements.

According to embodiments of the present invention, the present invention can provide the most effective fitness program to a user through a personalized fitness program recommendation system based on an artificial intelligence algorithm.

According to embodiments of the present invention, in the process of extracting user recognition and features in artificial intelligence-based image recognition, the present invention can perform the user's image information feature extraction even in a situation where an obstruction factor exists. There is an effect of improving the recognition rate by complementarily using artificial intelligence techniques in image recognition through image recognition.

Even if it is an effect not explicitly mentioned herein, the effect described in the following specification expected by the technical features of the present invention and the provisional effect thereof are treated as described in the specification of the present invention.

1 is a block diagram illustrating a fitness assistance system according to an embodiment of the present invention.
2 is a block diagram illustrating a processor of a fitness assistance system according to an embodiment of the present invention.
3 is an exemplary diagram showing the configuration of a fitness assistance system according to an embodiment of the present invention.
4 is a flowchart illustrating a method of operating a fitness assistance system according to an embodiment of the present invention.
5 is a flowchart illustrating selection of a personalized fitness program by a fitness assistance system according to an embodiment of the present invention.
6 is a flowchart illustrating a fitness process through a fitness assistance system according to an embodiment of the present invention.
7 is an exemplary diagram illustrating an image recognition model process of a fitness assistance system according to an embodiment of the present invention.
8 is a flowchart illustrating a fitness assistance method according to an embodiment of the present invention.

Hereinafter, in describing the present invention, when it is determined that the subject matter of the present invention may be unnecessarily obscured as matters apparent to those skilled in the art with respect to known functions related to the present invention, a detailed description thereof will be omitted, and some embodiments of the present invention It will be described in detail through exemplary drawings. However, the present invention may be implemented in various different forms, and is not limited to the described embodiments. In addition, in order to clearly describe the present invention, parts not related to the description are omitted, and the same reference numerals in the drawings indicate the same members.

The term and/or includes a combination of a plurality of related stated terms or any of a plurality of related stated terms.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. It should be.

The suffixes "module" and "unit" for constituent elements used in the following description are given or used interchangeably in consideration of only the ease of writing the specification, and do not themselves have a distinct meaning or role from each other.

Terms such as first and second may be used to describe various components, but the components should not be limited by terms. The above terms are used only for the purpose of distinguishing one component from another component.

The present invention relates to a game-based artificial intelligence fitness assistance system and method.

1 is a block diagram illustrating a fitness assistance system according to an embodiment of the present invention, and FIG. 2 is a block diagram illustrating a processor of a fitness assistance system according to an embodiment of the present invention. As shown in FIG. 1, the fitness assistance system 10 includes a display unit 100, an object recognition unit 200, and a processor 300. The fitness assistance system 10 may omit some of the various components exemplarily illustrated in FIG. 1 or may additionally include other components.

The fitness assistance system 10 is a fitness assistance system in which game elements are grafted, and as a complementary means of giving up fitness due to the absence of continuous motivation, fitness by adding game elements such as fitness battles, character growth, and ranking among multiple users. It can be consistently motivated. The fitness assistance system 10 may perform a game that utilizes unity through interactions between a plurality of users as well as a fitness battle between users described above. In addition, the fitness assistance system 10 is not restricted by location.

The fitness assistance system 10 can be applied to the smart fitness field, provides a personalized fitness program in consideration of personal characteristics such as the user's gender, age, body type, and exercise purpose, and provides a game according to fitness achievement level after fitness is completed. Continuous motivation can be provided through character implementation rewards.

The fitness assistance system 10 may include fitness competition content between users, character growth content, ranking content, and the like using mobile game elements. In addition, the fitness assistance system 10 may recommend a personalized fitness program through an artificial intelligence algorithm that processes information such as body information, gender, age, and exercise purpose of a target object.

The target object is a user who uses the fitness assistance system 10 and is a person who assists fitness using the fitness assistance system 10.

The fitness assistance system 10 may recommend a fitness program suitable for an individual. In addition, in recognizing the target object and extracting features, the fitness assistance system 10 may perform image information feature extraction of the target object in a situation in which an obstruction factor exists.

The fitness assistance system 10 performs image recognition through the Kinect 210, and may improve the recognition rate by complementarily using an artificial intelligence technique.

The fitness assistance system 10 is not limited in exercise equipment used in a fitness program performed by the target object. Exercise equipment may use not only small exercise equipment such as dumbbells and gym balls, but also bulky exercise equipment such as treadmills and cycles.

The fitness assistance system 10 may induce continuous motivation for exercise through a game in which objects using the fitness assistance system 10 compete or cooperate. Continuous motivation is not necessarily limited to a game that competes or cooperates, and may be content capable of inducing interest while a target object performs an exercise motion.

The image recognition model of the fitness assistance system 10 may be used based on a convolutional neural network (CNN). This is not necessarily limited.

A convolutional neural network (CNN) is a type of deep neural network (DNN), one or several convolutional layers, a pooling layer, and a fully connected layer. connected layers). A convolutional neural network (CNN) has multiple layers connected through a network and includes a hidden layer. The layer may include parameters, and the parameters of the layer include a set of learnable filters. A convolution filter can be applied to the filter. The parameters include weights and/or biases between nodes.

The fitness assistance system 10 can be applied to a smart fitness service, a content using artificial intelligence-based image recognition, a platform for a smart fitness service, a variety of content through image recognition, and interactive content through application of a mobile game.

The display unit 100 may provide fitness content related to fitness to a target object of the fitness assistance system.

The display unit 100 may be divided left and right to extract a standard object and a motion image of a target object of the fitness assistance system 10. The standard object represents an image of a fitness assistant trainer, and may be an image representing a shape that a target object using the fitness assistant system 10 can see and perform fitness with.

The display unit 100 may display (i) the matching rate, (ii) the number of movements of the target object, (iii) the target number of movements of the target object, and (iv) information on the amount of heat consumed by the target object at the top or bottom. The information located at the top or bottom of the display unit 100 is not necessarily limited to the above-described information, and may further include information that can help the movement of the target object.

When the motion matching rate of the target object falls below a preset value, the display unit 100 displays the body organs of the target object whose matching rate is lower on the motion image of the target object, and may output a motion correction guidance image to increase the matching rate. have.

The object recognition unit 200 may detect the motion of the target object and collect motion information of the target object. As shown in FIG. 1, the object recognition unit 200 includes a Kinect 210 and an image acquisition unit 220. The object recognition unit 200 may omit some of the various components exemplarily illustrated in FIG. 1 or may additionally include other components.

The Kinect 210 detects and recognizes the motion of the target object, and may detect Kinect information of the target object. Kinect information may include movement of a target object. Kinect 210 can play a program of fitness content with gestures, voices, and the entire body without a controller.

Kinect 210 generates Kinect information by detecting the motion of the target object. For example, the Kinect 210 generates link information between a feature point and a feature point by inputting an image of a target object. The feature point may represent a joint node, but is not limited thereto.

According to an embodiment of the present invention, fitness content includes game content, a motion image of a target object, a motion image of a standard object, a match rate, the number of movements of the target object, the number of exercise targets of the target object, information on the amount of calories consumed by the target object, etc. Content for assisting fitness may be included, but is not limited thereto.

The Kinect 210 includes an IR Emitter, a Color Sensor, an IR Depth Sensor, a Tilt Motor, a Microphone Array, and the like. The Kinect 210 transmits infrared rays to scan the target object of the fitness assistance system 10, and the infrared rays reaching the body of the target object are reflected and received. The Kinect 210 checks the distance per pixel according to the reflected infrared rays, and the image processing software can recognize the target object in real time. The Kinect 210 may determine the motion of the target object by recognizing the bone joint of the target object.

The image acquisition unit 220 may detect the motion of the target object and collect image information of the target object. According to an embodiment of the present invention, the image acquisition unit 220 may be a camera, and is not limited thereto, and may be formed as a device that detects the motion of the target object and collects image information of the target object.

According to an embodiment of the present invention, the image acquisition unit 220 may be used to prevent a reduction in recognition rate due to an obstructive factor when the motion and voice detection of the target object through the Kinect 210 is not smooth. .

Therefore, according to an embodiment of the present invention, the fitness assistance system 10 preferentially uses the Kinect 210 to detect motion information of the target object, and when the target object is not recognized smoothly, the image acquisition unit By using the image recognition model 331 learned based on the image information collected through 220, a motion characteristic may be detected by recognizing a target object.

The processor 300 detects the motion state according to the motion of the target object based on motion information of the target object, and controls the motion state according to the motion of the target object and the manner in which fitness content is provided to the display unit 100. have. As shown in FIG. 1, the processor 300 includes a display control unit 310, a program selection unit 320, an image processing unit 330, and a game execution unit 340. The processor 300 may omit some components or additionally include other components among the various components exemplarily illustrated in FIG. 1.

The display controller 310 may control a predetermined area of the display unit 100 to form a predetermined brightness, and control the display unit 100 to provide fitness-related fitness content.

When the object information of at least one of (i) body information, (ii) age, (iii) gender, (iv) body type, and (v) exercise purpose for the target object is input, the program selection unit 320 is based on the object information. You can select a program of fitness content.

Referring to FIG. 2, the program selection unit 320 includes an information integration unit 322, an object information feature generation unit 324, and an object information feature classification unit 326. The program selection unit 320 may omit some of the various components exemplarily illustrated in FIG. 2 or may additionally include other components.

The information integration unit 322 may integrate the input target object information.

The object information feature generation unit 324 may generate an object information feature by extracting the integrated object information through a feature extraction algorithm.

The object information feature classifier 326 may cluster object information features and classify the clustered object information features into a plurality of groups.

The program selection unit 320 may recommend a program of fitness content suitable for a target object of the fitness assistance system 10 based on a plurality of groups classified by the object information feature classification unit 326.

The process performed by the program selection unit 320 will be described in detail later with reference to FIG. 4.

The image processing unit 330 may (i) recognize a target object based on the Kinect information detected by the Kinect 210 to detect motion characteristics according to the movement, or (ii) the image acquisition unit 220 Based on the image information, the input image of the target object is applied to the image recognition model 331 to recognize the target object, and a motion characteristic according to the movement of the target object may be detected based on the image information.

The image processing unit 330 labels the area of the target object based on the extracted motion characteristics of the target object, and the labeling moves according to the movement of the target object. The image processing unit 330 may determine a matching rate by comparing a motion characteristic of a standard object and labeling.

Labeling is a method of grouping and numbering adjacent pixel values to identify objects, and is a method of grouping adjacent pixels and determining them as one object.

The game execution unit 340 may execute interactive game content according to an operation of a target object and another target object connected through a network. The display unit 100 may superimpose the motion scene of another target object of the interactive game content executed by the game execution unit 340 and output the motion scene of the target object.

The interactive game content may be formed interactively, but is not limited thereto. Interactive means interactive, interactive, and is a program that can input and output as if a target object communicates with another target object.

Referring to FIG. 2, the image recognition model 331 of the image processing unit 330 includes an outline extracting unit 332, an outline merging unit 334, and a feature extracting unit 336. The image recognition model 331 may extract shape and shape features by extracting and merging contour features of an input image based on a convolutional neural network (CNN).

According to an embodiment of the present invention, the image recognition model 331 is a matrix operation performed to transform an image into a certain pattern, and when the same filter is applied to the entire image, it is possible to detect whether or not the feature exists in the data. . The image recognition model 331 may extract features from an image, classify it, and output a classification result. If the result of matching the features of the image is the same, it is determined as the same image.

The contour extractor 332 may extract contour information of the body of the target object. The contour extracting unit 332 may extract contours such as a line frequently detected in an image such as a point or an edge.

According to an embodiment of the present invention, the contour extracting unit 332 extracts the contour by applying the contour filter, and if the contour is the result value is high, and if it is not the contour or is not similar to the contour, the result value is zero. Can be calculated close.

The contour merging unit 334 may merge the contour information extracted from the contour extracting unit 332 to collect body shape information of the target object. The contour merging unit 334 recognizes and merges a model such as a circle or a triangle, and may be merged into the shape of each body part of the target object.

The body feature extraction unit 336 may determine each body structure of the target object based on the body shape information of the target object, and recombine each body structure. The fitness assistance system 10 may recognize the target object based on each recombined body structure.

If the fitness assistance system 10 fails to extract the motion feature of the target object, it attempts to recognize it again using the Kinect 210, and if the recognition is not smooth, the image information collected through the image acquisition unit 220 is Based on this, the extraction of contour feature information can be performed again.

The fitness content of the fitness assistance system 10 may induce interest and motivation of a target object through a fitness match between objects using the fitness assistance system 10. The fitness match may be executed by the game execution unit 340.

According to an embodiment of the present invention, in the fitness match between objects, the fitness achievement index of the target object may be calculated based on the match rate. According to an embodiment of the present invention, the coincidence rate may mean a degree to which a motion characteristic of a target object and a motion characteristic of a standard object coincide. The display unit 100 may superimpose and output an exercise scene of a competitor in a fitness match between objects.

The fitness match between objects may include a ranking system that reinforces a character of a target object according to achievement using a fitness achievement index and assigns a ranking between objects based on a fitness achievement index.

3 is an exemplary diagram showing the configuration of a fitness assistance system according to an embodiment of the present invention.

Components of the fitness assistance system 10 may be located as shown in FIG. 3, and positions of the components of the fitness assistance system 10 are not necessarily limited thereto.

The Kinect 210 and the image acquisition unit 220 of the object recognition unit 200 of the fitness assistance system 10 are located at positions capable of detecting the motion of the target object. In addition, the display unit 100 of the fitness assistance system 10 may be located in a place where the target object of the fitness assistance system 10 can check content. The processor 300 may be located in a place where image information and feature information can be exchanged with the display unit 100 and the object recognition unit 200.

Referring to FIG. 3, the target object and the image acquisition unit 220 of the fitness assistance system 10, and the image acquisition unit 220 and the processor 300 may be located in places where image information of the target object can be exchanged. . In addition, the processor 300 of the fitness assistance system 10 and the display unit 100 and the display unit 100 and the target object may exchange extracted feature information.

The display unit 100 may be formed as a general display device, may be a display device formed for the fitness assistance system 10, and may be output through a home appliance formed as a display device such as a computer or a television.

The Kinect 210 of the object recognition unit 200 is configured to detect the Kinect information by first detecting motion information of the target object, and the image acquisition unit 220 can collect the image information of the target object in real time. It can be configured to have a performance.

The processor 300 may be configured to detect an operation state according to a movement of a target object of the collected image information.

Hereinafter, a fitness exercise process through the fitness assistance system 10 will be described in accordance with the flow.

4 is a flowchart illustrating a method of operating a fitness assistance system according to an embodiment of the present invention.

The operation method of the fitness assistance system 10 includes a login step (S100), a game content use step (S200), a fitness content use step (S300), a personalized fitness program selection step (S400), and a fitness assistance system 10. And a fitness step (S500), a game character implementation step (S600) according to a result after the fitness is ended, and a content use end step (S700).

The target object of the fitness assistance system 10 may log in to the fitness assistance system 10 to perform a fitness exercise (S100). In step S100, when the target object logs in to the fitness assistance system 10, information on the target object is input.

The target object of the fitness assistance system 10 may determine whether to use the game content (S200) when the login (S100) of the fitness assistance system 10 is completed.

In step S300, the fitness assistance system 10 may determine whether to use fitness content, and if fitness content is used, step S400 is performed, and when fitness content is not used, determining whether to use the game content (S200). You can go back to the stage.

The personalized fitness program selection step (S400) will be described in detail with reference to FIG. 5. 5 is a flowchart illustrating selection of a personalized fitness program by a fitness assistance system according to an embodiment of the present invention.

According to an embodiment of the present invention, the personalized fitness program selection step S400 may be performed through the program selection unit 320 of the fitness assistance system 10.

In the step of selecting a personalized fitness program (S400), when object information on a target object is input to the fitness assistance system 10, the step of integrating the input information (S410), the step of performing a feature extraction algorithm (S420), and the extracted features In accordance with the clustering step (S430), performing a classification algorithm for each feature group (S440), and recommending a personalized fitness program according to the group in which the features are classified (S450).

When object information of a target object such as body information, body type, age, gender, and exercise purpose of the target object is input, the fitness assistance system 10 may combine the input object information of the target object into one (S410). Step S410 is performed by the information integration unit 322 of the program selection unit 320.

The information of the integrated object goes through a feature extraction algorithm (S420). In step S420, the program selection unit 320 of the fitness assistance system 10 may extract a feature of the input object information through a feature extraction algorithm. Step S420 is performed by the object information feature generation unit 324 of the program selection unit 320.

According to an embodiment of the present invention, step S420 may include feature extraction as to whether the target object should increase or decrease the weight, skeletal muscle mass, or body fat mass through body information of the target object. Further, in step S420, a part that the target object needs to exercise centrally through the body shape of the target object may be extracted, and features of the part to be exercised through the exercise purpose of the target object may be extracted.

When step S420 is completed through the above-described process, the fitness assistance system 10 performs clustering (S430) according to the extracted features. Clustering is a process of grouping and remembering items that are similar or related to each other, and among the extracted features, features that are similar or related to each other can be grouped together.

The clustered extracted features go through a classification algorithm for each feature group (S440). In step S440, the program selection unit 320 of the fitness assistance system 10 may classify the clustered extracted features through a feature group classification algorithm.

According to an embodiment of the present invention, step S440 may classify the clustered extracted features into groups. The groups can be classified into groups according to a number of characteristics, such as a group of men in their teens, a group of women in their 20s, and a group of reducing body fat mass for men in their teens.

The above-described steps S430 and S440 are performed by the object information feature classification unit 326 of the step program selection unit 320.

When a group is classified, the fitness assistance system 10 performs a step (S450) of recommending a customized fitness program according to the group to which the characteristics are classified.

In step S450, a group classified through step S440 is selected, and a group suitable for the target object of the fitness assistance system 10 may be selected.

When the fitness assistance system 10 selects a group suitable for the target object of the fitness assistance system 10 in step S440, a personalized fitness program suitable for the group is recommended.

The target object of the fitness assistance system 10 may perform fitness by selecting one of the personalized fitness programs recommended through the above-described personalized fitness program selection step S400.

When a fitness program is selected through step S400, the fitness assistance system 10 may perform step S500.

The fitness step (S500) through the fitness assistance system 10 will be described in detail with reference to FIG. 6. 6 is a flowchart illustrating a fitness process through a fitness assistance system according to an embodiment of the present invention.

According to an embodiment of the present invention, the fitness step S500 through the fitness assistance system 10 may be performed through the image processing unit 320 of the fitness assistance system 10.

In the fitness step (S500) through the fitness assistance system 10, when the Kinect information detected through the Kinect 210 is input, checking whether the recognition of the Kinect information is smooth (S510), the learned image recognition model ( 331) applying step (S520), target object recognition step (S530), target object image image collection step (S540), target object motion feature extraction step (S550), and feature extraction failure check step (S560). .

When the Kinect information detected through the Kinect 210 is input, the fitness assistance system 10 may determine whether the Kinect 210 is recognized smoothly (S510). If the recognition is smooth in step S510, step S530 is performed. If the recognition is not smooth, step S520 is performed through the image information collected through the image acquisition unit 220.

In step S520, when the image information collected through the image acquisition unit 220 is input, it is applied to the learned image recognition model 331 to detect a motion state according to the movement of the target object. A process of performing the learned image recognition model 331 will be described in detail with reference to FIG. 7.

7 is an exemplary diagram illustrating an image recognition model process of a fitness assistance system according to an embodiment of the present invention.

In step S520, sequential feature extraction and merging based on a convolutional neural network (CNN) that extracts shape and shape features by extracting and merging contour features of the input image through artificial intelligence-based image recognition. In step S520, a target object is recognized based on the extracted shape and shape information, and image information of the target object is collected to extract motion information of the target object.

When the image information collected through the image acquisition unit 220 is input, the fitness assistance system 10 may generate an input image according to the image information. The input image may extract contour features through step S522.

Step S522 refers to extracting contour information of the body structure of the target object.

According to an embodiment of the present invention, the contour feature extraction may be formed in a form in which the outer surface of the body of the target object is divided into lines. For example, the head of the target object is divided into quadrants and extracted as four contour information, and the neck may be divided into a number of contour information, such as one, two legs, and so on. Step S522 is performed by the contour extraction unit 332 of the image processing unit 330.

In step S524, the outlines are merged based on the outline information of the body structure of the target object extracted in step S522. In step S524, the body structure shape information of the target object may be collected by merging the outline information of step S522.

According to an embodiment of the present invention, contour merging is a process of merging a shape in which the outer surface of a body of a target object is split into lines. For example, the head of a target object divided into quadrants can be merged into head information by gathering three outlines of the head. The body information of the merged target object may be head, neck, arm, body, and leg information representing each body of the target object, and is not necessarily limited thereto, and may be information obtained by disassembling the body of the target object into a number as necessary. have. Step S524 is performed by the contour merging unit 334 of the image processing unit 330.

In step S526, the shape and shape features of the body shape information of the target object merged in step S524 may be extracted. In step S526, each body structure may be determined based on the merged body shape information in step S524, and features thereof may be extracted.

According to an embodiment of the present invention, the shape and shape feature extraction may recognize the body structure of the target object and label the output information, and the labeling may follow according to the movement of the target object by recognizing that the target object moves. . Step S524 is performed by the body feature extraction unit 336 of the image processing unit 330.

In the above-described step S520, the information formed through steps S522, S524, and S526 is recombined, post-processed, and may be reconstructed into an image.

The fitness assistance system 10 may recognize the shape of the target object through step S510 or step S520 (S530).

In step S540, when the shape of the target object is recognized in step S530, a target object image image may be collected.

In step S550, a motion feature of the target object may be extracted through the collected target object image image.

In step S560, it is determined whether or not the feature is extracted, and if the feature extraction fails, the process returns to step S510, and if the feature extraction is successful, the process returns to step S540. When the feature extraction is successful and the process returns to step S540, a target object image image may be newly collected.

The fitness assistance system 10 collects the image image of the target object of the fitness assistance system 10 through the process of step S500 described above, and repeats the process of extracting the motion characteristics of the target object to obtain the The motion coincidence rate can be determined by comparing the motion and the motion of the target object.

The target object performs fitness through the process of step S500, and when the fitness is finished, step S600 may be performed.

Step S600 may implement a game character according to the result after the fitness is ended. For example, through the fitness achievement index performed in step S500, the character of the target object can be reinforced according to the achievement level of the target object, and a ranking among objects is given based on the achievement index, and rewards such as game items or game money are given accordingly Can be given.

The fitness assistance system 10 may change the game item worn by the target object as the game character level of the target object increases through reinforcement of the target object character, and the game item may be purchased through game money. . Interest and motivation may be induced in the target object of the fitness assistance system 10 through reinforcement and decoration of the target object character.

The fitness assistance system 10 may perform step S700 when the compensation according to the fitness result is divided through step S600.

In step S700, it is determined whether the use of the fitness content is ended. When continuing to use the fitness content, the fitness assistance system 10 returns to step S300 and checks whether or not the fitness content is used.

In FIGS. 4 to 6, it is interposed that each process is sequentially executed, but this is only illustrative, and those skilled in the art are shown in FIGS. 4 to 6 within a range not departing from the essential characteristics of the embodiment of the present invention. By changing the described order, executing one or more processes in parallel, or adding other processes, various modifications and variations may be applied.

8 is a flowchart illustrating a fitness assistance method according to an embodiment of the present invention. The fitness assistance method may be performed by the fitness assistance system, and detailed descriptions of operations performed by the fitness assistance system and overlapping descriptions will be omitted.

The fitness assist method includes providing fitness content related to fitness to a target object of a fitness assistance system (S810), collecting motion information of the target object by detecting the motion of the target object (S820), and providing motion information of the target object. Based on the detection of the motion state according to the movement of the target object, and controlling the manner in which the fitness content is provided to the display (S830).

In the step of collecting motion information of the target object (S820), the steps of detecting the Kinect information of the target object by detecting the motion and voice of the target object, and the steps of collecting image information of the target object by detecting the motion of the target object Includes.

In the step of collecting the image information of the target object, in the step of detecting the Kinect information of the target object, when the motion and voice detection of the target object is not smooth, the image information of the target object is Collection can be carried out.

The operation state according to the movement of the target object is detected based on the motion information of the target object, and in the step of controlling the manner in which fitness content is provided to the display unit (S230), a predetermined area of the display unit is controlled to form a predetermined brightness, Controlling to provide fitness-related fitness content to the display unit, at least one of (i) body information, (ii) age, (iii) gender, (iv) body shape, and (v) exercise purpose for the target object Information is input, selecting a program of fitness content based on object information, extracting features of movement of a target object based on Kinect information or image information, and applying image information to the image recognition model 331 And detecting an operation state according to the movement of the target object.

In FIG. 8, each process is intervened to be executed sequentially, but this is only illustrative, and those skilled in the art may change the order shown in FIG. 8 without departing from the essential characteristics of the embodiment of the present invention. Or, by executing one or more processes in parallel, or adding other processes, various modifications and variations may be applied.

The operations according to the present embodiments may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. Computer-readable medium refers to any medium that has participated in providing instructions to a processor for execution. The computer-readable medium may include program instructions, data files, data structures, or a combination thereof. For example, there may be a magnetic medium, an optical recording medium, a memory, and the like. Computer programs may be distributed over networked computer systems to store and execute computer-readable codes in a distributed manner. Functional programs, codes, and code segments for implementing this embodiment may be easily inferred by programmers in the art to which this embodiment belongs.

The present embodiments are for explaining the technical idea of the present embodiment, and the scope of the technical idea of the present embodiment is not limited by these embodiments. The scope of protection of this embodiment should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present embodiment.

10: fitness assist system
100: display unit
200: object recognition unit
300: processor

Claims (13)

In a fitness assistance system for assisting fitness,
A display unit that provides fitness content for fitness of the target object to the target object using the fitness assistance system;
An object recognition unit that detects a motion of the target object and collects motion information of the target object; And
Fitness assistance including a processor that detects motion characteristics according to motion of the target object based on motion information of the target object, compares it with motion characteristics of a standard object, and controls the manner in which the fitness content is provided to the display unit system. The method of claim 1,
The processor includes a game execution unit for executing interactive game content according to the operation of the target object and another target object connected through a network,
And the display unit outputs an exercise scene of the other target object. The method of claim 1,
The object recognition unit,
A Kinect for detecting Kinect information of the target object by detecting a motion of the target object; And
An image acquisition unit configured to detect a motion of the target object and collect image information of the target object,
And the image acquisition unit is used to prevent a reduction in recognition rate due to an obstruction factor when motion detection of the target object through the Kinect is not smooth. The method of claim 3,
The processor,
A display control unit controlling a predetermined area of the display unit to form a predetermined brightness, and controlling the display unit to provide fitness content related to the fitness;
When at least one of (i) body information, (ii) age, (iii) gender, (iv) body type, and (v) exercise purpose for the target object is input, the fitness content is displayed based on the object information. A program selection unit for selecting a program; And
(i) Recognizing the target object based on the Kinect information to detect motion characteristics according to the movement of the target object, or (ii) applying an input image of the target object to an image recognition model A fitness assistance system including an image processing unit that recognizes an object and detects a motion characteristic according to a motion of the target object based on the image information. The method of claim 4,
The program selection unit,
An information integration unit for integrating the object information on the input target object;
An object information feature generator for generating an object information feature by extracting the integrated object information through a feature extraction algorithm; And
And an object information feature classifier for clustering the object information features and classifying the clustered object information features into a plurality of groups,
And the program selection unit recommends a program of the fitness content suitable for the target object based on the classified plurality of groups. The method of claim 4,
The image recognition model,
An outline extracting unit for extracting outline information of the target object;
A contour merging unit for merging the contour information extracted by the contour extracting unit to collect body shape information of the target object; And
And a body feature extraction unit for determining each body structure of the target object based on the body shape information of the target object and recombining the body structure,
A fitness assistance system, characterized in that to recognize the target object based on the recombined body structure. The method of claim 4,
The image processing unit labels the area of the target object based on the detected movement characteristic according to the movement of the target object, and the labeling moves according to the movement of the target object, and determines the movement characteristic and the labeling of the standard object. Fitness assistance system, characterized in that to determine the matching rate by comparing. The method of claim 7,
The display unit is divided left and right to extract a motion image of the standard object and a motion image of the target object,
The display unit displays (i) the matching rate, (ii) the number of movements of the target object, (iii) the target number of movements of the target object, and (iv) information on the amount of heat consumed by the target object at the top or bottom. Fitness assistance system. The method of claim 8,
When the matching rate of the target object falls below a preset value, the display unit displays a body organ of the target object whose matching rate is lowered on a motion image of the target object, and outputs a motion correction guidance image to increase the matching rate. And
And the processor calculates a fitness achievement index of the target object based on the matching rate. The method of claim 9,
The processor,
Performing character reinforcement for reinforcing the character of the target object according to the achievement level using through the fitness achievement level index,
And performing a ranking system for assigning a ranking among the target objects based on the fitness achievement index. In the fitness assistance method using a fitness assistance system for assisting fitness,
Providing fitness content for fitness of the target object to the target object using the fitness assistance system through a display unit;
Detecting a motion of the target object and collecting motion information of the target object; And
Fitness assistance comprising the step of detecting a motion characteristic according to the motion of the target object based on the motion information of the target object, comparing it with the motion characteristic of a standard object, and controlling the manner in which the fitness content is provided to the display unit Way. The method of claim 11,
Collecting motion information of the target object,
Detecting a motion of the target object and detecting Kinect information of the target object; And
Detecting a motion of the target object and collecting image information of the target object,
The collecting of the image information of the target object is performed to prevent a reduction in recognition rate due to an obstructive factor when the motion detection of the target object is not smoothly detected in the step of detecting the Kinect information of the target object. How to do a fitness aid. The method of claim 12,
Controlling the manner in which the fitness content is provided to the display unit,
Controlling a predetermined area of the display unit to form a predetermined brightness, and controlling fitness content related to the fitness to be provided to the display unit;
At least one of (i) body information, (ii) age, (iii) gender, (iv) body type, and (v) exercise purpose for the target object is input, and the fitness content is based on the object information. Selecting a program of; And
(i) Recognizing the target object based on the Kinect information to detect motion characteristics according to the movement of the target object, or (ii) applying an input image of the target object to an image recognition model Recognizing an object and detecting a motion characteristic according to a motion of the target object based on the image information.

Images