KR20220061511A - Device, method and program for guiding exercise posture and momentum - Google Patents

Abstract

The present invention relates to a device for guiding an exercise posture and exercise rate which provides feedback on an exercise posture of a user based on the exercise posture of the user recognized in an exercise image of the user, and calculates and feeds back the exercise rate of the user, thereby preventing overtraining. The device comprises: a communication unit; a skeleton acquisition unit; a storage unit; and a processor.

Description

Exercise posture and momentum guiding device, method and program {Device, method and program for guiding exercise posture and momentum}

The present invention relates to a device for guiding an exercise posture and amount of exercise, and more particularly, to an apparatus for guiding a user's exercise posture and amount of exercise by analyzing an image captured by a camera.

Recently, as the importance of well-being and self-management is increasing day by day, the number of people who exercise regularly is also increasing.

It is very important to exercise continuously while maintaining a correct posture and not excessive exercise.

If the exercise is performed in the wrong posture, the effect of the exercise decreases, and in severe cases, an injury may occur, and the same problem may occur even if the amount of exercise cannot be controlled.

In order to prevent these problems, there is a method such as exercising with a personal trainer, but there is no suitable method for those who cannot afford this.

Accordingly, there is a need for a device that provides a service for guiding a user's exercise posture and amount of exercise, such as a personal trainer, but at present, such a technology is not disclosed or its accuracy is remarkably low.

Republic of Korea Patent Publication No. 10-2016-0084703, (2016.07.14)

The present invention for solving the above problems is to provide feedback information by acquiring skeleton data from a user's exercise image and comparing it with the exercise posture of an expert.

In addition, the present invention intends to determine whether the user is overtraining by calculating and comparing the total exercise volume and the exercise volume performed by the user from the user's exercise image.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

Exercise posture and exercise amount guide apparatus according to an embodiment of the present invention for solving the above-described problems, a communication unit for receiving a user exercise image taken through a camera; Based on the image and depth data in the user movement image, a skeleton acquisition unit that acquires skeleton data, a storage unit that stores reference data including an exercise posture of an expert according to an exercise type, and the skeleton data and the reference data are compared and , calculates exercise posture accuracy based on the comparison result, calculates and compares the user's total exercise volume and performed exercise volume, determines whether the user is overtraining based on the comparison result, and determines the calculated exercise posture accuracy and a processor for controlling to derive and output feedback information based on at least one of the overtraining.

In addition, the processor selects reference data matching the movement type of the movement image from among the reference data and compares it with the skeleton data, and when the comparison result shows that the angle value of the movement part is out of a preset reference range, the user's It is characterized in that the exercise posture is judged to be incorrect.

In addition, the storage unit further stores body part information related to the exercise posture for each exercise type, and the processor determines that, as a result of the comparison, the position of the body part not involved in the exercise type being performed by the user deviates from a preset reference value or more. , characterized in that it is determined that muscles unnecessary for the type of exercise are being used.

In addition, when it is detected that the user starts the first set of a specific exercise type, the processor calculates 1RM (Repetition Maximum) based on at least one of the exercise weight of the first set, the number of repetitions and the accuracy, and the accuracy is When the preset reference range is satisfied, the total exercise volume is calculated based on the 1RM.

Also, the processor may calculate the total exercise volume based on Equation 1 below.

[Equation 1]

Total Workout Volume = 70% of the user's 1RM weight x 10 (rep) x 8 (set)

In addition, the processor calculates a rest time between each exercise set of the user based on the user exercise image, and as the exercise of each set progresses, the exercise weight of the corresponding set, the number of repetitions, and the rest before the start of the exercise of the set It is characterized in that the volume of the exercise performed of the set is calculated based on the time.

In addition, the processor is characterized in that it calculates the exercise volume to be performed based on Equation 2 below.

[Equation 2]

Volume of exercise performed per set = weight x number of reps x rest (sec) / 180 (sec)

In addition, the processor calculates a total exercise volume by accumulating the calculated exercise volume, and when the total exercise volume exceeds the total exercise volume, it is determined as overtraining and controlling to output feedback information characterized.

In addition, the exercise posture and exercise amount guide method according to an embodiment of the present invention for solving the above-described problems, the step of receiving a user exercise image photographed from a camera, based on the image and depth data in the user exercise image, Acquiring skeleton data, comparing the skeleton data and the reference data, calculating the exercise posture accuracy based on the comparison result, calculating and comparing the total exercise volume and the exercise volume performed by the user, and the comparison result Determining whether the user is overtrained based on It is characterized in that it includes a storage in which reference data including the movement posture of the stored.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium for recording a computer program for executing the method may be further provided.

According to the present invention as described above, by acquiring the skeleton data from the user's exercise image and comparing it with the exercise posture of the expert, there is an effect that can guide the user to the correct exercise posture.

In addition, according to the present invention, there is an effect of preventing overtraining of the user by calculating and comparing the total exercise volume and the exercise volume performed by the user from the user's exercise image.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 and 2 are block diagrams of an exercise posture and momentum guide system according to an embodiment of the present invention.
3 is a flowchart of an exercise posture and an exercise amount guide method according to an embodiment of the present invention.
4 is a diagram illustrating that reference data including an exercise posture of an expert for each exercise type is stored in the storage unit.
5 is a diagram illustrating that the user is exercising in a proper posture.
FIG. 6 is a diagram illustrating that the processor provides feedback information according to FIG. 5 .
7 is a diagram illustrating that the user is exercising with an incorrect posture.
FIG. 8 is a diagram illustrating that the processor provides feedback information according to FIG. 7 .
9 is a diagram illustrating that the user is using the wrong muscle during exercise.
FIG. 10 is a diagram illustrating that the processor provides feedback information according to FIG. 9 .
11 is a diagram illustrating a standard table for calculating 1RM.
12 and 13 are diagrams illustrating an example of outputting whether or not the user overtrained through the output unit.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Before the description, the meaning of the terms used in this specification will be briefly described. However, it should be noted that, since the description of the term is for the purpose of helping the understanding of the present specification, it is not used in the meaning of limiting the technical idea of the present invention unless explicitly described as limiting the present invention.

1 and 2 are block diagrams of an exercise posture and momentum guide system 10 according to an embodiment of the present invention.

3 is a flowchart of an exercise posture and an exercise amount guide method according to an embodiment of the present invention.

4 to 13 are various exemplary views of an exercise posture and an exercise amount guide method according to an embodiment of the present invention.

Hereinafter, with reference to FIGS. 1 to 13 , an exercise posture and an exercise amount guide apparatus 100 and a method according to an embodiment of the present invention will be described.

The exercise posture and exercise amount guide apparatus 100 according to an embodiment of the present invention is performed by an information processing device 100 such as a computer, and a fitness center equipped with various exercise equipment so that several people can exercise The feedback information may be output through an output unit 170 (eg, the kiosk device 100 having a display module) provided for each exercise device by being installed in the .

Alternatively, the exercise posture and exercise amount guide server may receive a user exercise image captured by the terminal 200 (eg, a smartphone) and provide feedback information to the terminal 200 .

In this case, the server provides a service application, and the user may install the service application in his/her terminal 200 and use the exercise posture and exercise amount guide service.

Therefore, in an embodiment of the present invention, the exercise posture and exercise amount guide apparatus 100 providing data and information to the user's terminal 200 means providing it through a service application installed in the user terminal 200 .

As described above, the exercise posture and momentum guide device 100 and the method can be implemented in various forms, so that the photographing unit and the output unit 170 may be included in the configuration of the exercise posture and momentum guide device 100 or external The configuration may be used to receive only the captured image and control the processor 110 to output feedback information through the external output unit 170 .

Referring to FIG. 1 , the exercise posture and momentum guide apparatus 100 according to an embodiment of the present invention includes a processor 110 , a communication unit 120 , a skeleton obtaining unit 130 , a storage unit 140 , and a calculation unit 150 . ), an authentication module 160 and an output unit 170 .

However, in some embodiments, the device 100 may include fewer or more components than those illustrated in FIG. 1 .

First, the communication unit 120 of the device 100 receives a user movement image captured by the camera 210 . (S110)

As described above, the communication unit 120 may receive an image photographed through the at least one camera 210 installed in the exercise place.

In this case, the camera 210 may be a single camera and an RGBD camera 210 in which a ToF sensor is combined.

However, the usable camera 210 is not limited thereto, and anything can be applied as long as the processor 110 can analyze the user's exercise image.

For example, since the camera 210 capable of measuring depth data is recently used in a smartphone, a user motion image captured by the camera of the smartphone may be received.

In addition, the processor 110 may process the user's exercise image by using images captured by two or more cameras 210 installed at different locations.

In one embodiment, before S110, the processor 110 may perform a user authentication process through the authentication module 160 .

For example, when the fingerprint recognition sensor is provided in the kiosk device 100 installed in the exercise place, the processor 110 loads the user's fingerprint information stored in the storage unit 140 to perform user authentication, A corresponding user may be logged into the kiosk device 100 .

In addition, the processor 110 may perform authentication by recognizing the user's face in the user's motion image captured by the camera 210 .

As described above, since various methods are applicable to the method by which the processor 110 performs user authentication through the authentication module 160, the practitioner of the present invention can easily select the method.

In addition, when the user uses the exercise posture and exercise amount guide service for the first time, the user inputs personal information including his/her physical condition (eg, height, weight, etc.) through the registration process, and the exercise posture and exercise quantity guide device 100 is Such user information is stored in the user DB of the storage unit 140 or the server 200 .

In addition, the device 100 may receive data such as an InBody measurement result when a user subscribes to a service, and the user's body change information from body information or new InBody measurement result data input after a certain time has elapsed after subscription , exercise effect information, etc. may be derived and provided to the user's terminal 200 .

S110 Next, the processor 110 controls the skeleton acquisition unit to acquire skeleton data based on the image and depth data in the user's motion image. (S120)

More specifically, the skeleton acquisition unit extracts key points by specifying each joint of the body based on the RGB image and depth data included in the user's motion image, and connects each key point to obtain the skeleton. extract

In this case, the skeleton obtaining unit may extract a key point using an extraction model learned by machine learning so as to extract a human key point from within the RGB image.

In addition, the skeleton obtaining unit acquires the skeleton data by setting 3D coordinates to the extracted skeleton based on the depth data included in the user's motion image.

Through the above process, the processor 110 acquires 3D skeleton data through the skeleton acquisition unit.

S120 Next, the processor 110 compares the skeleton data and the reference data through the calculator 150 , and calculates the exercise posture accuracy based on the comparison result. (S130)

The processor 110 calculates and compares the total exercise volume and the exercise volume performed by the user through the calculator 150 , and determines whether the user is overtrained based on the comparison result. (S140)

The processor 110 derives feedback information based on at least one of the calculated exercise posture accuracy and overtraining, and controls the feedback information to be output through the output unit 170 . (S150)

4 is a diagram illustrating that reference data including an exercise posture of an expert for each exercise type is stored in the storage unit 140 .

As shown in FIG. 4 , the storage unit 140 of the device 100 stores reference data including the exercise posture of the expert for each type of exercise, so that the processor 110 includes the skeleton data obtained from the user exercise image and the exercise of the expert. It is possible to compare the reference data, which is the posture, and calculate the accuracy of the user's exercise posture through the calculator 150 .

In an embodiment of the present invention, the exercise posture and momentum guide apparatus 100 may receive reference data from the reference DB of the server 300 and store it in the storage unit 140 as shown in FIG. 1 .

In some embodiments, reference data may be received and stored according to an exercise machine or apparatus in which the exercise posture and exercise amount guide device 100 is installed.

However, the present invention is not limited thereto, and the exercise posture and exercise amount guide device 100 may be implemented as a server device, and all reference data is stored in the storage unit 140 so that the processor 110 corresponds to each exercise machine and instrument. Reference data to be used may be loaded from the storage 140 and used.

In more detail, the processor 110 calculates an angle for each position of a key point that is each joint in the skeleton data including 3D data through the calculator 150 .

Then, the processor 110 may calculate the exercise posture accuracy by comparing the calculated angle with an angle value of reference data stored in the storage unit 140 .

In an embodiment, the calculator 150 may calculate the exercise posture accuracy by using an exercise posture accuracy calculation algorithm stored in the storage unit 140 . For example, the algorithm may be an algorithm for calculating the exercise posture accuracy for each angle according to the type of exercise.

At this time, the processor 110 selects the type of exercise currently being performed by the user based on information about at least one of the user's current position (meaning the current position in the exercise space), the exercise equipment being used by the user, and the user's exercise posture. can judge

In addition, the processor 110 may select reference data matching the type of exercise of the exercise image from among the reference data and compare it with the skeleton data.

5 is a diagram illustrating that the user is exercising in a proper posture, and FIG. 6 is a diagram illustrating that the processor 110 provides feedback information according to FIG. 5 .

Referring to FIG. 5 , the processor 110 acquires the skeleton data of the exercise part from the user's exercise image in which the user lifts the dumbbell, and as a result of measuring and analyzing the angle (A) of the arm, the reference data that is the exercise image of the expert The coincidence with 93% corresponds to that, it is determined that the user is exercising with the correct posture, and feedback information as shown in FIG. 6 is outputted and provided through the output unit 170 .

As described above, the output unit 170 in the embodiment of the present invention may be applied to the display unit of the kiosk device 100 or the user's terminal 200 capable of visually outputting the feedback information derived by the processor 110 . In addition, a speaker capable of outputting a voice may be further included.

Accordingly, the processor 110 may visually output the feedback information through the display unit of the output unit 170 , and when there is a voice message or a warning message to be delivered to the user, it may be output through the speaker.

To this end, in the embodiment of the present invention, the output unit 170 may include a display unit capable of outputting an image and an image, a speaker capable of outputting audio, and the like.

In addition, as shown in FIG. 6 , the processor 110 may output a button providing a tip for the current exercise type through the output unit 170, and when the user clicks/selects the Tip button, various tips for the corresponding exercise The output may be output through the output unit 170 .

For example, when an exercise corresponding to the current exercise type is performed, the processor 110 may output a body part helpful for muscle generation, a video of an expert's exercise posture demonstration, precautions, and the like as a tip.

7 is a diagram illustrating that the user is exercising with an incorrect posture, and FIG. 8 is a diagram illustrating that the processor 110 provides feedback information according to FIG. 7 .

Referring to FIG. 7 , the processor 110 acquires the skeleton data of the exercise part from the user's exercise image in which the user lifts the dumbbell, and as a result of measuring and analyzing the angle (B) of the arm, the degree of agreement with the reference data is 72 %, since it was calculated that it was less than the preset reference range, it was determined that the user was exercising with the wrong posture, and feedback information as shown in FIG. 8 is output and provided.

The processor 110 may derive and provide detailed feedback information by analyzing the user's incorrect posture in addition to deriving feedback information indicating that the current exercise posture is incorrect when deriving and outputting the feedback information.

In detail, the processor 110 relates to one or more key points involved in the type of exercise the user is currently performing, an exercise start point of each key point, an intermediate movement of each key point, and an exercise end point of each key point, skeleton data and Reference data can be compared and analyzed, and detailed analysis can be carried out at the point where the coincidence rate falls short of the reference range.

And, based on the detailed analysis result, the processor 110 may analyze what point is wrong in the user's exercise posture, and analyze the cause of the wrong posture to derive and provide feedback information.

In addition to the reference data including the exercise posture of the expert, the storage unit 140 of the device 100 stores data on a plurality of incorrect exercise posture types, and each of the incorrect exercise posture type data includes at least the occurrence of an incorrect exercise posture. One cause is stored.

Therefore, the processor 110 compares the skeleton data with the reference data, and if it is determined that the exercise posture accuracy is insufficient, searches for the user's exercise posture image in the storage unit 140 and selects a matching wrong exercise posture type, At least one cause of an incorrect exercise posture may be derived based on the big data and output through the output unit 170 .

In addition, when it is determined that the user's exercise posture accuracy is insufficient, the processor 110 simultaneously outputs the exercise posture image of the user and the exercise posture of the expert included in the reference data through the output unit 170, so that the user can display the exercise posture on one screen. You can compare your posture with that of a professional.

In addition, the processor 110 accumulates information such as the type of exercise performed by the user, the number of repetitions of each exercise, and the exercise weight of each set from the moment it is determined that the user has started exercising on the day, thereby providing the user's exercise information. create

And, when it is determined that the user has finished exercising on the day, the processor 110 provides the generated exercise information to the output unit 170 or the user's terminal 200, and the accumulated user's exercise information is It may include information on the type of exercise performed at work, weight information, repetition number, exercise accuracy, and the like.

The processor 110 stores the user's exercise information generated in this way in the user DB of the storage unit 140 or the server 300 together with the exercise date and time, manages the user's exercise information, and uses it later to provide feedback information can provide

Specifically, the processor 110 may calculate consumed calories based on the generated exercise information, compare it with previously generated exercise information, and generate the comparison result as a chart to provide visual information.

For example, information on how much exercise ability (eg, weight, number of repetitions, etc.) for a specific exercise type has improved compared to the past may be provided.

9 is a diagram illustrating that the user is using the wrong muscle during exercise, and FIG. 10 is a diagram illustrating that the processor 110 provides feedback information according to FIG. 9 .

In the incorrect exercise posture illustrated in FIGS. 7 and 8 , when the angle value of the exercise part (key point) is out of a preset reference range, it is determined that the user's exercise posture is incorrect.

9 and 10 exemplify a case in which the user determines that the exercise posture is incorrect when a body part not involved in the current exercise type is used.

For example, while the user is doing dumbbell curl exercise, the arm angle is at the correct angle to perform the exercise posture, but if the user raises the dumbbell by recoiling by moving the waist or legs, the effect of the exercise decreases or the body Other areas may be strained.

In addition, as shown in FIG. 9 , the angle (A) of the arm is at the correct angle in the process of the user performing the dumbbell curl exercise, and the user is exercising in a proper exercise posture, but the shoulder is tilted or the dumbbell is lifted through recoil that moves the shoulder. can be raised

Referring to FIG. 9, the user lifts the dumbbell to an angle corresponding to the correct posture as shown in FIG. 5 and the angle (A) of the arm maintains the correct exercise posture, but it is illustrated that the shoulder line is tilted too much from C there is.

Accordingly, when the position of a body part that is not involved in the type of exercise that the user is currently performing is moved (deviates) by more than a preset reference value, the processor 110 may determine that muscles not required for the type of exercise are being used.

In an embodiment, the storage unit 140 of the apparatus 100 further stores body part information related to the exercise type in reference data including the exercise posture of the expert for each exercise type.

Therefore, in addition to comparing the skeleton data with the reference data, the processor 110 monitors the skeleton data to calculate the degree of movement of a body part that is not involved in the type of exercise currently being exercised, and based on this, the user determines the type of exercise currently being exercised. You can determine whether you are using muscles you don't need.

People have different appropriate exercise volumes, and exercise volume is a direct cause of muscle growth, and exercise efficiency can be increased through appropriate exercise volume and rest.

At this time, if you exercise with an exercise volume higher than your physical strength and physical condition, muscle fatigue increases and the exercise efficiency decreases, and in severe cases, the risk of injury also increases.

In order to solve the above-described problem, the exercise posture and exercise amount guide apparatus 100 according to an embodiment of the present invention calculates an appropriate exercise volume for each individual, calculates whether the user enters the overtraining stage, and adjusts the exercise volume of the user. It has the effect of regulating it properly.

In one embodiment, when it is detected that the user starts the first set of a specific exercise type, the processor 110 calculates 1RM (Repetition Maximum) based on at least one of the exercise weight of the first set, the number of repetitions, and the accuracy.

In this case, the processor 110 may calculate the total exercise volume based on 1RM when the accuracy satisfies a preset reference range.

In an embodiment of the present invention, 1RM is a force generated through one maximum contraction, and means the maximum weight that a user can lift in an accurate posture.

The processor 110 may update the 1RM to the latest information if the user performs the exercise, the posture accuracy score satisfies the reference range, and is higher than the previously stored 1RM.

11 is a diagram illustrating a standard table for calculating 1RM.

The storage unit 140 of the device 100 stores a standard table as shown in FIG. 11 , and the calculator 150 may calculate the user's 1RM by using this standard table.

When the user's previous 1RM information does not exist, the processor 110 may estimate the 1RM by using the user's body information, and when the 1RM is measured, the user's total exercise volume may be set.

In an embodiment, when the user's exercise posture accuracy score is less than a preset reference range, the processor 110 may derive and provide feedback information recommending the user to lower the weight, and the user's total exercise volume is will keep it as is.

As a result of various tests, the applicant was able to obtain the result that 8 sets, 30 to 60 repetitions with a weight equivalent to 1RM per muscle area show the greatest effect in the exercise volume of most people, and also corresponds to 1RM per set It was found that the best exercise effect was obtained when performing 10 to 12 repetitions with a weight equivalent to 70% of the weight.

Accordingly, the exercise posture and momentum guide apparatus 100 according to the embodiment of the present invention may calculate the total exercise volume through Equation 1 below.

In an embodiment, the processor 110 may calculate a rest time between each exercise set of the user based on the user's exercise image.

As the exercise of each set progresses, the processor 110 may calculate the exercise volume to be performed of the corresponding set based on the exercise weight of the corresponding set, the number of repetitions of the exercise, and the rest time before the start of the exercise of the corresponding set.

In addition, as a result of various tests conducted by the applicant, it was found that for most people, the most appropriate rest period between sets was 3 minutes.

Accordingly, the processor 110 may calculate the exercise volume for each set through Equation 2 below.

In this case, since there is no rest time before the first set, the processor 110 may calculate the exercise volume for each set of the first set by multiplying the weight by the number of repetitions.

The processor 110 repeats the above process every time the user's exercise sets are finished through the calculator 150 , and calculates the total exercise volume by summing the user's exercise volumes.

In addition, when the total exercise volume exceeds the total exercise volume, the processor 110 determines that the user has entered overtraining and outputs feedback information through the output unit 170 .

12 and 13 are diagrams illustrating an example of outputting whether the user overtrained or not through the output unit 170 .

The processor 110 may provide the output to the user through the output unit 170 as to whether the user is overtraining as shown in FIGS. 12 and 13 , and the calculation unit 150 as shown in FIGS. 12 and 13 . The calculated numerical value and visual information may be output together and provided.

In addition, when the user's total exercise volume reaches 100% of the total exercise volume as shown in FIG. 13 , the processor 110 outputs a warning message that the user's body is overtrained because it is overtraining if the user exercises more. can

In one embodiment, the processor 110 determines that the user has not checked the overtraining message when the user continues to exercise while the total exercise volume of the user reaches 100% of the total exercise volume, and the output unit A warning sound may be output through (170).

In addition, when the user continues to exercise while the user's total exercise volume reaches 100% of the total exercise volume, the processor 110 is an administrator (eg, a personal trainer, a fitness club) who manages an exercise place where the user is exercising. administrator) can be provided with a notification message.

As an embodiment, the device 100 may receive the user's biometric information measured by a wearable device (eg, a smart watch) worn by the user through the communication unit 120 .

In this case, the biometric information that can be received through the communication unit 120 may be any biometric information that can be measured by the wearable device of the user. Information can be applied.

In addition, the device 100 may receive data such as the user's body information and the InBody measurement result through the communication unit 120 , and the processor 110 may receive the user's body information and the InBody measurement result through the calculator 150 . It is possible to create a threshold of each user's biometric information based on the , and monitor the user's exercise index based on this.

Then, the processor 110 monitors the user's biometric information received in real time through the communication unit 120, and when specific biometric information approaches or exceeds a preset threshold, a warning message or A warning sound can be output.

For example, when the user's heart rate threshold is set to 150HR based on the user's body information and the InBody measurement result, the processor 110 warns the user to recommend lowering the exercise intensity when the user's heart rate exceeds 150HR during exercise A message or a warning sound may be output through the output unit 170 .

In one embodiment, when it is determined that the user's exercise today is over, the processor 110 controls the calculator 150 to calculate the user's total exercise volume, the total exercise volume performed, and the user's biosignals collected during the exercise time. Based on this, it is possible to calculate and provide the user's achievement of today's exercise.

For example, since the achievement of exercise may vary depending on the condition of the day, the processor 110 calculates and provides the exercise achievement of the user based on various information as described above, thereby allowing the user to measure the exercise achievement of the day. You can check and help make decisions such as setting up a future exercise schedule or taking a break.

In an embodiment, the processor 110 accumulates the exercise posture accuracy calculated for each exercise type of the user and stores it in the storage unit 140 as the average exercise posture accuracy.

In addition, the processor 110 may derive feedback information by comparing the exercise posture accuracy of the user's specific exercise type with the average exercise posture accuracy stored in the storage unit 140 , and output it through the output unit 170 .

For example, if it is repeated that the exercise posture accuracy of the user's specific exercise type falls below the first ratio (eg, 90%) compared to the average exercise posture accuracy stored in the storage unit 140, the user's condition today is poor. It is possible to derive feedback information to focus on the exercise posture and pay attention to the injury.

As another example, if it is repeated that the exercise posture accuracy of a specific exercise type of the user falls to a second rate or less (eg, 75%) compared to the average exercise posture accuracy stored in the storage unit 140, It is possible to derive feedback information suggesting that there is an abnormality in the muscle area or the possibility of an injury.

This is because if the accuracy is too low compared to the normal exercise posture accuracy is calculated, the wrong posture may be continuing because there is an abnormality in the user's body (muscle), so that the processor 110 derives and outputs feedback information. , it has the effect of warning the user to check his or her body condition.

Also, the processor 110 may derive a matching expert's exercise lecture image based on at least one exercise type in which the user's average exercise posture accuracy is lower than the reference value, and provide it to the user's terminal 200 .

In one embodiment, the processor 110 may calculate the user's basal metabolic rate based on the user's body information and the InBody measurement result stored in the storage unit 140 , and store it in the storage unit 140 .

In addition, the processor 110 may derive a recommended diet, a recommended meal amount, etc. based on the user's total exercise volume, total exercise volume and exercise time, and the user's basal metabolic rate and provide it to the user's terminal 200 .

As an embodiment, the processor 110 may receive and receive a target value for the value of at least one InBody item from the user terminal 200 .

In addition, the processor 110 recommends at least one type of exercise suitable for the user based on the target value of at least one InBody item input from the user, the measurement value of the current InBody item of the user, and the 1RM value of the user, and each exercise type. The weight, the number of sets to be performed, the number of repetitions of the exercise, and the type and time of aerobic exercise may be derived and provided to the user's terminal 200 .

For example, different people may have different exercise goals, such as increasing the amount of muscle, maintaining the current physique, or reducing body fat while maintaining the amount of muscle.

Accordingly, the processor 110 analyzes the user's current state (measured value of the recent InBody item) and the user's target state (the target value of the InBody item input from the user terminal 200), so that the user can use his/her own body as a user. It means designing and providing an exercise plan so that it can be made with the goal of

In one embodiment, the camera 210 installed in an exercise place (eg, a fitness club) is provided with an angle adjusting device 100 capable of adjusting the angle of the camera 210 .

When the user is authenticated and the user starts exercising, the processor 110 recognizes the user within the captured image of the camera 210 and controls the angle adjusting device 100 to track the recognized user so that the user can continue to shoot. .

According to the exercise posture and momentum guide method according to the embodiment of the present invention described above, the exercise posture is corrected by comparing the exercise posture of the user with the exercise posture of the expert (reference data), as well as calculating the amount of exercise and the user's intention It has the effect of preventing accidental overtraining.

The method according to an embodiment of the present invention described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The above-described program is C, C++, JAVA, machine language, etc. that a processor (CPU) of the computer can read through a device interface of the computer in order for the computer to read the program and execute the methods implemented as a program It may include code (Code) coded in the computer language of Such code may include functional code related to a function defining functions necessary for executing the methods, etc., and includes an execution procedure related control code necessary for the processor of the computer to execute the functions according to a predetermined procedure. can do. In addition, the code may further include additional information necessary for the processor of the computer to execute the functions or code related to memory reference for which location (address address) in the internal or external memory of the computer to be referenced. there is. In addition, when the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, the code uses the communication module of the computer to determine how to communicate with any other computer or server remotely. It may further include a communication-related code for whether to communicate and what information or media to transmit and receive during communication.

The storage medium is not a medium that stores data for a short moment, such as a register, a cache, a memory, etc., but a medium that stores data semi-permanently and can be read by a device. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the program may be stored in various recording media on various servers accessible by the computer or in various recording media on the computer of the user. In addition, the medium may be distributed in a computer system connected to a network, and a computer-readable code may be stored in a distributed manner.

The steps of a method or algorithm described in relation to an embodiment of the present invention may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing the technical spirit or essential features thereof. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

10: Exercise posture and momentum guide system
100: exercise posture and momentum guide device
110: processor
120: communication department
130: Skeleton Acquisition Department
140: storage
150: output unit
160: authentication module
170: output unit
200: terminal
210: camera

Claims (10)

a communication unit for receiving a user movement image taken through a camera;
a skeleton acquisition unit for acquiring skeleton data based on the image and depth data in the user's motion image;
a storage unit storing reference data including an exercise posture of an expert according to an exercise type; and
Comparing the skeleton data and the reference data, calculating an exercise posture accuracy based on the comparison result,
Calculating and comparing the user's total exercise volume and performed exercise volume, and determining whether the user is overtraining based on the comparison result,
A processor for controlling to derive and output feedback information based on at least one of the calculated exercise posture accuracy and the overtraining,
Exercise posture and momentum guide device.
According to claim 1,
The processor is
Among the reference data, reference data matching the movement type of the movement image is selected and compared with the skeleton data. characterized in that
Exercise posture and momentum guide device.
3. The method of claim 2,
The storage unit further stores information on body parts involved in the exercise posture for each exercise type,
As a result of the comparison, when the position of a body part not involved in the type of exercise the user is performing deviates from a preset reference value or more, the processor determines that a muscle unnecessary for the type of exercise is being used,
Exercise posture and momentum guide device.
According to claim 1,
The processor is
When it is detected that the user starts the first set of a specific exercise type, 1RM (Repetition Maximum) is calculated based on at least one of the exercise weight of the first set, the number of repetitions and the accuracy, and the accuracy satisfies a preset reference range characterized in that the total exercise volume is calculated based on the 1RM when
Exercise posture and momentum guide device.
5. The method of claim 4,
The processor is characterized in that it calculates the total exercise volume based on Equation 1 below,
Exercise posture and momentum guide device.
<Equation 1>
Total Workout Volume = 70% of the user's 1RM weight x 10 (rep) x 8 (set)
5. The method of claim 4,
The processor is
Calculating a rest time between each exercise set of the user based on the user exercise image,
As each set of exercise progresses, the exercise volume of the set is calculated based on the exercise weight of the set, the number of repetitions, and the rest time before the start of the exercise of the set,
Exercise posture and momentum guide device.
7. The method of claim 6,
The processor is characterized in that it calculates the exercise volume to be performed based on Equation 2 below,
Exercise posture and momentum guide device.
<Equation 2>
Volume of exercise performed per set = weight x number of reps x 180 (seconds) / rest time (seconds)
7. The method of claim 6,
The processor is
accumulating the calculated exercise volume to calculate a total exercise volume;
When the total exercise volume to be performed exceeds the total exercise volume, it is determined as overtraining, characterized in that the control to output feedback information,
Exercise posture and momentum guide device.
A method performed by a computer, comprising:
Receiving a user movement image taken from the camera;
acquiring skeleton data based on the image and depth data in the user's motion image;
comparing the skeleton data and the reference data, and calculating exercise posture accuracy based on the comparison result;
calculating and comparing the total exercise volume and the exercise volume performed by the user, and determining whether the user is overtraining based on the comparison result; and
Deriving and outputting feedback information based on at least one of the calculated exercise posture accuracy and the overtraining,
The computer is characterized in that it includes a storage unit in which reference data including the exercise posture of the expert according to the type of exercise is stored,
How to guide your exercise posture and momentum.
A recording medium having a program for executing the method of claim 9 in combination with a computer as hardware.

Images