KR102356685B1 - Home training providing system based on online group and method thereof - Google Patents

Abstract

The present invention relates to a system and a method for providing online group home training. According to the present invention, a home training providing method using an online group home training providing system comprises the steps of: grouping into a plurality of groups according to input plurality of participant information and athletic abilities from an input unit for receiving participant information and exercise ability information from a plurality of participants through a plurality of participant terminals connected to the online group home training system through a network; receiving an image captured by the participant terminal and providing it to a network-connected trainer terminal and other participant terminals; extracting exercise postures of the plurality of participants from the captured images, respectively; calculating a similarity between each exercise posture extracted from the plurality of participants and a pre-stored exercise posture of a trainer; if the calculated similarity is greater than the reference value, counting the number of exercises of the corresponding motion by determining that the motion is performed in the correct posture; and providing the number of exercises for each of a plurality of participants to the trainer terminal. According to the present invention, since a skeleton correction technique is used, it is possible to accurately determine the exercise capacity of a plurality of participants. Also, the present invention is provided non-face-to-face, it is possible to receive training without restrictions on location.

Description

HOME TRAINING PROVIDING SYSTEM BASED ON ONLINE GROUP AND METHOD THEREOF

The present invention relates to a home training providing system and method based on an online group, and to a home training providing system and method based on an online group for providing non-face-to-face group training to participants in need of training. it's about

Due to the expansion of the conditions for enjoying sports, many people can easily enjoy various sports. In addition, in recent years, professional personal training has been in the spotlight due to the improvement of living standards as well as the acquisition of more specialized knowledge about sports.

Professional personal training has the advantage of being able to prevent sports injuries due to incorrect posture in advance and obtaining efficient exercise effects through personalized instruction, but there is also a disadvantage that is accompanied by a high cost.

In order to realize the effect of personal training at a lower cost against the disadvantage of such high cost, a product that recognizes the user's motion using a depth camera or a low-cost motion sensor and helps the user to correct his/her own posture are appearing a lot.

However, these techniques record the user's motion and compare the user's posture with a predefined correct posture. have.

In addition, although various poses and motions are recognized to some extent through the current motion sensor or image sensor, there is a disadvantage in that it is not possible to accurately estimate and display the movement distance and wide area moved by the trainee.

Therefore, in order to solve these shortcomings, the skeleton structure (skeleton) is derived by estimating each joint point of the human body, and a skeleton correction technique is used that extracts the rotation value of the joint point based on the difference between the frames of the recognized depth map. .

Therefore, there is a need for a training method using a skeleton correction technique.

The technology that is the background of the present invention is disclosed in Korean Patent Laid-Open No. 10-2015-0114141 (published on October 12, 2015).

An object of the present invention is to provide an online group home training providing system and method for providing non-face-to-face group training to participants in need of training.

According to an embodiment of the present invention for achieving this technical problem, in a method for providing home training using an online group home training providing system, a plurality of participants can be transferred from a plurality of participants through a plurality of participant terminals connected to the network to the online group home training providing system. Receiving an input of receiving information and athletic ability information, grouping into a plurality of groups according to the inputted plurality of participant information and athletic ability, receiving an image captured by the participant terminal and network-connected trainer terminal and other providing to the participant terminal, extracting the exercise postures of the plurality of participants from the captured images, respectively, and calculating the similarity between the exercise postures extracted from the plurality of participants and the pre-stored exercise postures of the trainer. Calculating, when the calculated similarity is greater than a reference value, determining that the operation is performed in the correct posture and counting the number of exercises for the corresponding operation, providing the number of exercises for each of a plurality of participants to the trainer terminal include

When the exercise of the participants included in the group is finished, calculating a ratio of the number of successful motions to the number of motion attempts for each participant included in the group is included in the group by using the calculated ratio The method may further include resetting the plurality of participants into one or more groups.

The step of resetting the group includes classifying the exercise ability of each of the plurality of participants into a plurality of grades according to the ratio, grouping one or more participants to which the same grade is assigned, each of the participants included in the reset group It may include providing the captured image of the participant to participant terminals corresponding to the remaining participants.

In the step of extracting the movement postures, respectively, the movement postures and joint angles of the plurality of participants may be extracted by applying a skeleton correction technique to the plurality of captured images.

In the step of providing to the trainer terminal, the exercise posture of the participant generated through the skeleton correction technique is superimposed on the photographed image of the participant, and the degree of similarity to the movement of the participant and the number of successes for a specific movement are provided together. can do.

According to another embodiment of the present invention, in an online group home training providing system for providing home training, participant information and exercise ability information from a plurality of participants through a plurality of participant terminals connected to the network to the online group home training providing system An input unit for receiving input, a grouping unit for grouping into a plurality of groups according to the inputted plurality of participant information and exercise ability, a communication unit for receiving an image captured by the participant terminal and providing it to a network-connected trainer terminal and other participant terminals , an extraction unit that extracts the exercise postures of the plurality of participants from the captured image, a calculator that calculates a similarity between each exercise posture extracted from the plurality of participants and a pre-stored exercise posture of the trainer, the above; When the calculated similarity is greater than the reference value, a control unit that determines that the operation is performed in the correct posture and counts the number of exercises of the corresponding operation, and a providing unit that provides the number of exercises of a plurality of participants to the trainer terminal through the communication unit include

As described above, according to the present invention, since the skeleton correction technique is used, the exercise ability of a plurality of participants can be accurately determined, and since it is provided non-face-to-face, training can be received without restriction of place.

In addition, by providing the match rate and the number of exercises on the screen of a plurality of participants, it is possible to accurately determine the exercise ability of the current participant, and through regrouping, users with similar exercise levels are matched to provide more suitable exercise information from the trainer's point of view. Users can also improve their satisfaction by exercising with users with similar exercise skills.

1 is a view for explaining a system for providing group home training according to an embodiment of the present invention.
2 is a configuration diagram for explaining the configuration of a management server of a system for providing group home training according to an embodiment of the present invention.
3 is a flowchart illustrating a method for providing group home training according to an embodiment of the present invention.
FIG. 4 is a view for explaining step S330 of FIG. 3 .
FIG. 5 is a view for explaining step S350 of FIG. 3 .
FIG. 6 is a view for explaining step S390 of FIG. 3 .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily carry out the present invention. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

Then, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them.

Hereinafter, a configuration of a system for providing group home training according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2 .

1 is a diagram for explaining a system for providing group home training according to an embodiment of the present invention.

As shown in FIG. 1 , the online group home training providing system 100 according to an embodiment of the present invention includes a management server 110 , a trainer terminal 120 , and a participant terminal 130 .

First, the management server 110 receives a plurality of network-connected participant information and exercise ability information connected to the online group home training providing system 100, classifies it into a plurality of groups according to the input information, and a plurality of extracts each exercise posture of the participants, calculates the similarity between each exercise posture and the previously stored exercise posture of the trainer, and if the calculated similarity is greater than the reference value, it is determined that the exercise was performed with the correct posture Count the number of workouts of the motion, and provide the number of workouts for each of the plurality of participants to the trainer terminal.

Next, the trainer terminal 120 is a terminal used by the trainer of the online group home training providing system 100 , and the participant terminal 130 is a terminal used by the participant of the online group home training providing system 100 .

In this case, as for the trainer terminal 120 and the participant terminal 130 , the trainer terminal 120 may be changed to the participant terminal 130 or the participant terminal 130 may be changed to the trainer terminal 120 according to the subject used.

Here, the terminal is a portable user terminal, and may be implemented as a device capable of exchanging information by connecting to a network by wire or wirelessly, such as a notebook computer, a smart pad, or a smart phone.

In this case, the management server 110 , the trainer terminal 120 , and the participant terminal 130 are linked through a wired or wireless network.

Here, the wired or wireless network may use Bluetooth, Zigbee, Wi-Fi, WiBro, short-range wireless communication, and LAN.

2 is a configuration diagram for explaining the configuration of a management server of a system for providing group home training according to an embodiment of the present invention.

As shown in FIG. 2 , the management server 110 includes an input unit 111 , a grouping unit 112 , a communication unit 113 , an extraction unit 114 , an operation unit 115 , a control unit 116 and a providing unit 117 . include

First, the input unit 111 receives participant information and athletic ability information from a plurality of participant terminals 130 connected through a wired or wireless network.

Next, the grouping unit 112 groups a plurality of groups according to the inputted plurality of participant information and exercise ability.

Next, the communication unit 113 receives the image captured by the participant terminal and provides it to the network-connected trainer terminal and other participant terminals.

Next, the extraction unit 114 extracts the exercise postures of the plurality of participants from the captured image, respectively.

At this time, the extraction unit 114 extracts the movement postures and joint angles of the plurality of participants by applying the skeleton correction technique to the plurality of captured images.

Next, the calculating unit 115 calculates a similarity between each exercise posture extracted from a plurality of participants and a pre-stored exercise posture of the trainer, respectively.

Next, when the calculated similarity is greater than the reference value, the controller 116 determines that the operation is performed with the correct posture and counts the number of times of movement of the corresponding movement.

In addition, when the exercise of the participants included in the corresponding group is finished, the control unit 116 calculates a ratio of the number of successful motions to the number of motion attempts for each participant included in the group, and uses the calculated ratio to calculate the number of successful motions for each participant in the group. reset the plurality of participants included in one or more groups.

Then, the controller 116 classifies the exercise ability of each of the plurality of participants into a plurality of grades according to the ratio, groups one or more participants to which the same grade is assigned, and captures images of each participant included in the reset group. is provided to the participant terminals corresponding to the remaining participants.

Next, the providing unit 117 provides the number of workouts of each of the plurality of participants to the trainer terminal through the communication unit 113 .

Hereinafter, a method for providing group home training according to an embodiment of the present invention will be described with reference to FIGS. 3 to 6 .

3 is a flowchart illustrating a method for providing online group home training according to an embodiment of the present invention.

First, the input unit 111 receives participant information and exercise ability information from a plurality of participants through a plurality of participant terminals 130 connected to a network ( S310 ).

Here, the participant information is the participant's personal information such as each participant's name, gender, and age, and the exercise ability means the maximum number of exercise postures.

In this case, the management server 110 provides information on a plurality of exercise postures to the participant terminal 130 so that the number of times for each exercise posture can be input.

For example, exercise ability is input from the participant, such as 50 lunges or 30 pull-ups.

Next, the grouping unit 112 groups a plurality of groups according to the inputted plurality of participant information and exercise ability (S320).

In this case, the grouping unit 112 may classify the groups into upper, middle, and lower groups according to the exercise abilities of the plurality of participants, and may classify the groups into respective groups according to men or women.

For example, the grouping unit 112 may classify the exercise ability into an upper group if the exercise capacity is 150 or more lunges, a middle group if 75 or more and less than 150 times, and a lower group if the exercise capacity is less than 75.

Also, the grouping unit 112 may assign a score according to the number of times for each exercise posture, and set a plurality of groups by using the sum of the scores for each exercise posture.

Next, the communication unit 113 receives the image captured by the participant terminal 130 and provides it to the network-connected trainer terminal 120 and other participant terminals 130 (S330).

FIG. 4 is a view for explaining step S330 of FIG. 3 .

That is, as shown in FIG. 4 , the communication unit 113 provides the information to the trainer terminal 120 and other participant terminals 130 .

In this case, each participant can be set to cover his or her face or a part where personal information is confirmed according to their selection.

In addition, the configuration of the screen may be changed according to each participant.

Next, the extraction unit 114 extracts the exercise postures of the plurality of participants from the captured images, respectively (S340).

At this time, the extraction unit 114 extracts each exercise posture from each image taken by using the skeleton correction technique.

Here, the skeleton correction technique is a method of deriving a skeletal structure (skeleton) by estimating each joint point of the human body and extracting the rotation value of the joint point based on the recognized difference between frames. used to extract

In addition, in order to improve the accuracy of the skeleton correction technique, the extracted exercise posture is learned by applying a machine learning algorithm.

Next, the calculating unit 115 calculates the degree of similarity between each extracted exercise posture and the pre-stored exercise posture of the trainer (S350).

FIG. 5 is a diagram for explaining step S350 of FIG. 3 .

That is, as shown in FIG. 5 , the exercise posture of each participant extracted through step S340 is matched with the pre-stored exercise posture of the trainer.

Then, the calculating unit 115 calculates a degree of similarity between the exercise posture of each participant and the pre-stored exercise posture of the trainer.

Next, the controller 116 compares the calculated similarity with a reference value ( S360 ).

In this case, the reference value is a preset value and may be changed according to a trainer's selection or a group of participants.

At this time, if the calculated similarity is equal to or greater than the reference value, the controller 116 determines that the participant has operated with the correct posture and counts the number of times of exercise of the corresponding movement ( S370 ).

On the other hand, if the calculated similarity is smaller than the reference value, the controller 116 determines that the participant did not operate with the correct posture and does not count the number of times of exercise of the corresponding movement (S380).

Then, the providing unit 117 provides each exercise frequency of the plurality of participants to the trainer terminal and other participant terminals (S390).

FIG. 6 is a view for explaining step S390 of FIG. 3 .

That is, as shown in FIG. 6 , the providing unit 117 provides the number of successes and the degree of similarity for a specific motion at the upper end of the video of each participant.

In addition, the providing unit 117 provides the participant's motion posture overlaid on the photographed image of the participant through the skeleton correction technique.

Next, the control unit 116 determines whether the exercise of the participants included in the group is terminated (S400).

At this time, if the exercise of the participants included in the group is not finished, steps S340 to S400 are re-executed.

Next, when the exercise of the participants included in the group is finished, the controller 116 calculates a ratio of the number of successful motions to the number of motion attempts for each participant included in the group ( S410 ).

For example, if the number of motion attempts of participant 1 is 100 and the number of successful motions is 75, the control unit 116 calculates the ratio as 75%, the number of motion attempts of participant 2 is 150, and the number of successful motions If is 75 times, the control unit 116 calculates the ratio as 50%.

Next, the controller 116 resets the plurality of participants included in the corresponding group into one or more groups by using the ratio calculated from step S410 ( S420 ).

That is, if the ratio of the number of successful motions to the number of motion attempts is 90% in a group in which the ratio of the number of successful motions to the number of motion attempts is 70%, the control unit 116 sets the participant to a ratio of the number of successful motions to the motion attempts of 90%. Reset to % group.

On the contrary, if the ratio of the number of successful motions to the number of motion attempts is 50% in a group in which the ratio of the number of successful motions to the number of motion attempts is 70%, the control unit 116 sets the participant as the ratio of the number of successful motions to the number of motion attempts. Reset to 50% group.

As described above, according to an embodiment of the present invention, since the skeleton correction technique is used, the exercise ability of a plurality of participants can be accurately determined, and since it is provided non-face-to-face, training can be received without restriction of place.

In addition, by providing the match rate and the number of exercises on the screens of a plurality of participants, it is possible to accurately determine the exercise ability of the current participant.

Although the present invention has been described with reference to the embodiment shown in the drawings, this is merely exemplary, and those of ordinary skill in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Accordingly, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

100: online group home training providing system,
110: management server, 111: input unit,
112: grouping unit, 113: communication unit,
114: extraction unit, 115: calculation unit,
116: control unit, 117: providing unit;
120: trainer terminal, 130: participant terminal

Claims (10)

In the online group home training providing method using the online group home training providing system,
receiving participant information and athletic ability information from a plurality of participants through a plurality of participant terminals connected to a network to an online group home training providing system, and grouping into a plurality of groups according to the inputted plurality of participant information and exercise capability;
receiving the image captured by the participant terminal and providing it to a network-connected trainer terminal and other participant terminals;
extracting the exercise postures of the plurality of participants from the captured images, respectively;
Calculating a degree of similarity between each exercise posture extracted from the plurality of participants and a previously stored exercise posture of the trainer, respectively;
When the calculated similarity is greater than the reference value, counting the number of times of movement of the corresponding movement by determining that the operation was performed with the correct posture;
providing each of the number of workouts of a plurality of participants to the trainer terminal;
When the exercise of the participants included in the group is finished, calculating a ratio of the number of successful motions to the number of motion attempts for each participant included in the group; and
Resetting the plurality of participants included in the corresponding group to one or more groups using the calculated ratio,
The step of extracting each of the exercise postures,
By applying a skeleton correction technique to the plurality of images taken and extracting the movement postures and joint angles of the plurality of participants, respectively,
The step of resetting the group is
Classifying the exercise ability of each of the plurality of participants into a plurality of grades according to the ratio, and grouping one or more participants to which the same grade is assigned; and
A method of providing online group home training, comprising providing an image captured by each participant included in the reset group to participant terminals corresponding to the remaining participants. delete delete delete According to claim 1,
The step of providing to the trainer terminal is,
An online group home training providing method for providing the participant's motion posture generated through the skeleton correction technique on the photographed image of the participant by superimposing it, and providing both the degree of similarity to the participant's motion and the number of successes for the specific motion. In the online group home training providing system for providing online group home training,
an input unit for receiving participant information and athletic ability information from a plurality of participants through a plurality of participant terminals connected through a network;
A grouping unit for grouping into a plurality of groups according to the inputted plurality of participant information and exercise ability;
a communication unit for receiving the image captured by the participant terminal and providing it to the network-connected trainer terminal and other participant terminals;
an extraction unit for extracting the exercise postures of the plurality of participants from the captured images, respectively;
a calculation unit that calculates a degree of similarity between each exercise posture extracted from the plurality of participants and a previously stored exercise posture of the trainer;
When the calculated similarity is greater than the reference value, the controller determines that the operation is performed with the correct posture and counts the number of times of movement of the corresponding movement; and
and a providing unit that provides the number of workouts of a plurality of participants to the trainer terminal through the communication unit,
The extraction unit,
By applying a skeleton correction technique to the plurality of images taken and extracting the movement postures and joint angles of the plurality of participants, respectively,
The control unit is
When the exercise of the participants included in the group is finished, the ratio of the number of successful motions to the number of motion attempts is calculated for each participant included in the group, and the plurality of groups included in the group is calculated using the calculated ratio. reset the participants into one or more groups, classify the exercise ability of each of the plurality of participants into a plurality of grades according to the ratio, group one or more participants with the same grade, and each included in the reset group An online group home training providing system that provides the captured images of the participants to the participant terminals corresponding to the remaining participants. delete delete delete 7. The method of claim 6,
The providing unit,
An online group home training providing system that provides the participant's motion posture generated through the skeleton correction technique on the captured image of the participant and provides a similarity to the participant's motion and the number of successes for a specific motion.

Images