KR102425255B1 - Apparatus and Method for Processing of Exercise Information - Google Patents

Abstract

The present invention relates to an exercise information processing apparatus and method.
The exercise information processing apparatus according to the present invention includes a camera unit for photographing a user's exercise image, a type determining unit for determining the user's exercise type based on the exercise image, and a user's exercise motion based on the exercise image It may include an operation determining unit for determining the.

Description

Apparatus and Method for Processing of Exercise Information

The present invention relates to an exercise information processing apparatus and method.

With the improvement of living standards, modern people's interest in health is rapidly increasing. As a part of this, the number of modern people who exercise for disease prevention and personal hobby is gradually increasing.

In recent years, personal training (PT) in which you exercise 1:1 with a trainer is in the spotlight.

However, PT has a disadvantage in that it is expensive.

If the user performs the exercise alone, there is a problem in that it is difficult to determine the accuracy of the user's motion or the appropriateness of the exercise performed by the user.

The present invention was derived to solve the above problems, and an object of the present invention is to provide an exercise information processing apparatus and method for photographing a user's exercise image, and analyzing the captured exercise image to provide exercise information.

The exercise information processing apparatus according to the present invention includes a camera unit for photographing a user's exercise image, a type determining unit for determining the user's exercise type based on the exercise image, and an exercise motion of the user based on the exercise image It may include an operation determining unit for determining the.

In addition, it may further include a time determining unit for measuring the user's exercise time based on the exercise image.

The apparatus may further include an information providing unit configured to provide recommendation information to the user based on at least one of information on the type of exercise, information on the exercise action, and information on the exercise time.

In addition, the information providing unit may further provide information on achievement to the user based on at least one of information on the exercise type, information on the exercise motion, and information on the exercise time.

In addition, when the type of exercise is an exercise using a weight mechanism, it may further include a mechanism determining unit for determining a load (Load) set in the weight mechanism.

In addition, the motion determining unit may further provide information on the similarity between the user's exercise motion and a preset reference motion.

In addition, further comprising an object recognition unit for recognizing a moving object by analyzing the motion image, the object recognition unit extracts a background from the motion image, and recognizes a part having a color different from the extracted background as the moving object can do.

The apparatus may further include a mobility calculator for classifying the movement of the moving object by varying the brightness over time, and calculating the mobility based on the direction and degree of the change in the brightness.

In addition, the type determining unit may determine the type of exercise of the user based on the movement.

In addition, the motion determining unit may determine the user's motion motion based on the motion.

The exercise information processing method according to the present invention includes the steps of: photographing a user's exercise image, determining the user's exercise type based on the exercise image, and determining the user's exercise motion based on the exercise image may include steps.

The method may further include measuring a user's exercise time based on the exercise image.

The method may further include providing recommended information to the user based on at least one of information on the type of exercise, information on the exercise motion, and information on the exercise time.

In addition, the method further includes providing information on achievement to the user, wherein the information on achievement is based on at least one of information on the type of exercise, information on the exercise motion, or information on the exercise time. can be derived by

In addition, when the type of exercise is an exercise using a weight mechanism, the method may further include determining a load set in the weight mechanism.

The method may further include providing information on similarity (accuracy) between the user's exercise motion and a preset reference motion.

In addition, the method further includes a recognition step of recognizing a moving object by analyzing the motion image, wherein in the recognition step, a background is extracted from the motion image, and a part having a color different from the extracted background is recognized as the moving object. can do.

The method may further include classifying the movement of the moving object by varying the brightness over time, and calculating mobility based on the direction and degree of the change in brightness.

In addition, it is possible to determine the type of exercise of the user based on the movement.

In addition, it is possible to determine the exercise motion of the user on the basis of the movement.

The exercise information processing apparatus and method according to the present invention can provide information on the user's exercise motion, number of exercises, etc. by analyzing the user's exercise image, so that objective and accurate exercise information can be provided to the user at a lower cost. It works.

1 is a view for explaining the configuration of an exercise information processing apparatus according to the present invention;
2 to 33 are diagrams for explaining the exercise information processing method according to the present invention,
34 to 37 are diagrams for explaining another exercise information processing method according to the present invention.

Hereinafter, an exercise information processing apparatus and method according to the present invention will be described in detail with reference to the accompanying drawings.

Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. This is not intended to limit the present invention to a specific embodiment, it can be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention.

In describing the present invention, terms such as first, second, etc. may be used to describe various components, but the components may not be limited by the terms. The above terms may be used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

The term and/or may include a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but other components may exist in between. can be understood On the other hand, when an element is referred to as being “directly connected” or “directly connected” to another element, it may be understood that the other element does not exist in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression may include the plural expression unless the context clearly dictates otherwise.

In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, and one or more other features It may be understood that the existence or addition of numbers, steps, operations, components, parts or combinations thereof is not precluded in advance.

Unless defined otherwise, all terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries may be interpreted as having meanings consistent with the meanings in the context of the related art, and unless explicitly defined in the present application, they are interpreted in an ideal or excessively formal meaning. it may not be

In addition, the following embodiments are provided to more completely explain to those with average knowledge in the art, and the shapes and sizes of elements in the drawings may be exaggerated for clearer explanation.

1 is a view for explaining the configuration of an exercise information processing apparatus according to the present invention.

Referring to FIG. 1 , the exercise information processing apparatus 10 according to the present invention includes a control unit 100 , a camera unit 300 , an output unit 400 , a user input unit 500 , a memory unit 600 , and a communication unit 700 . may include.

The camera unit 300 may capture a predetermined image under the control of the controller 100 . For example, the camera unit 300 may capture an exercise image of the user. Alternatively, the camera unit 300 may capture an image of a predetermined exercise area (such as a gym).

The camera unit 300 may include at least one camera.

The output unit 400 may output predetermined information so that the user can check it according to the control of the control unit 100 . In detail, the output unit 400 may output information about the exercise, for example, information about the reference motion of the exercise, the reference number of times, and the like so that the user can check it.

The output unit 400 may include a display unit 410 and an audio output unit 420 .

The display unit 410 may display various information as images. The voice output unit 420 may output various information as voice.

The user input unit 500 may be used for a user to input a predetermined command. The user input unit 500 may include at least one of a key input unit, a touch input unit, and a voice input unit.

The memory unit 600 may store various information under the control of the controller 100 . For example, the memory unit 600 may store information on a reference number of times, a reference operation, a reference time, and the like.

The communication unit 700 may communicate with other devices. For example, the communication unit 700 may transmit information on exercise or an edited exercise image to another device or a predetermined page (website) designated in advance under the control of the controller 100 .

The controller 100 may control the overall operation of the exercise information processing apparatus 10 .

The controller 100 may acquire various information about the user's exercise based on the exercise image captured by the camera unit 300 .

The controller 100 may determine the start and end of the user's exercise.

The control unit 100 includes a type determining unit 110, an operation determining unit 120, a number determining unit 130, a time determining unit 140, an instrument determining unit ( 150 ), a tracking unit 160 , a path determining unit 170 , a preference determining unit 180 , an object recognition unit 190 , a movement determining unit 200 , an information providing unit 210 and an editing unit 220 . can do.

The type determining unit 110 may determine the type of exercise for the user's exercise based on the user's exercise image captured by the camera unit 300 .

The motion determining unit 120 may determine the user's motion motion based on the motion image.

The number of times determining unit 130 may determine the number of times of exercise of the user based on the exercise image.

The number of times determining unit 130 may count the number of times of exercise when the user's exercise motion matches the preset reference motion by more than a preset reference ratio.

The time determining unit 140 may determine the user's exercise time based on the exercise image.

The equipment determining unit 150 may determine the type of the exercise equipment selected by the user.

In addition, when the exercise type is an exercise using a weight mechanism, the mechanism determining unit 150 may determine a load set in the weight mechanism.

The tracker 160 may track a user selected from among a plurality of users as a target within a preset exercise area.

The path determining unit 170 may determine information on a path within the exercise area of the user selected based on the exercise image.

The preference determining unit 180 may determine at least one user's preference for the exercise equipment or at least one user's preference for the warm type.

The object recognition unit 190 may recognize a moving object by analyzing the motion image.

The mobility calculating unit 200 may classify the movement of the moving object recognized by the object recognition unit 190 by varying the brightness over time, and may calculate the mobility based on the direction and degree of the change in brightness.

The information providing unit 210 may provide recommended information to the user based on at least one of information on the type of exercise, information on the number of exercises, or information on the exercise time.

In addition, the information providing unit 210 may provide various information obtained by analyzing the exercise image to the user, other devices, and/or a website designated in advance.

The image editing unit 220 may extract/edit a highlight image from the user's exercise image.

The exercise information processing apparatus 10 of the configuration of FIG. 1 may be implemented with various types of hardware. For example, the exercise information processing apparatus 10 according to the present invention may be manufactured in the form of a mobile communication terminal such as a smart phone, or may be manufactured in the form of a fixed terminal such as a CCTV.

An exercise information processing method using the exercise information processing apparatus having such a configuration will be described in detail below with reference to the accompanying drawings.

2 to 37 are diagrams for explaining the exercise information processing method according to the present invention. Hereinafter, a description of the content described above may be omitted.

Referring to FIG. 2 , in the exercise information processing method according to the present invention, first, the exercise setting processing apparatus 10 may be set ( S100 ).

In the setting step, it is possible to arrange the camera unit 300 at a position where a motion image can be captured.

Alternatively, the exercise information processing apparatus 10 may be set to the exercise image capturing mode.

If necessary, the user may be authenticated by inputting information such as the user's ID or password (PW).

When a photographing command is input, the camera unit 300 may photograph a user's exercise image under the control of the controller 100 ( S400 ). For example, as in the case of FIG. 3 , it is possible for the exercise information processing device 10 in the form of a mobile communication terminal to photograph an image of the user H exercising.

Thereafter, the controller 100 may analyze the motion image captured by the camera unit 300 ( S300 ).

In addition, the controller 100 may determine various kinds of exercise information as a result of analyzing the exercise image ( S400 ).

Thereafter, the controller 100 may provide various information based on the determined information ( S500 ).

In the information providing step, the communication unit 700 may transmit the information determined by the control unit 100 according to the control of the control unit 100 to another device or a preset homepage.

The method of analyzing the exercise video is as follows.

Referring to FIG. 4 , in the step of analyzing the motion image ( S300 ), a background may first be extracted from the motion image ( S310 ). In detail, by comparing a plurality of image frames, it is possible to determine a portion with no or very little motion as the background, and extract the background according to the determination result.

For example, as in the case of FIG. 5 , when the first frame (A) and the second frame (B) after the first frame (A) are compared, the second frame (B) has a predetermined value. It can be seen that the object (Object, OB) is included, and the object (OB) is not included in the first frame (A).

In this case, the object OB newly added to the temporally late second frame B may be recognized as the moving object OB.

In the first frame (A) and the second frame (B), the image of the remaining part except for the object OB is almost unchanged. In other words, the image of the remaining part except for the object OB hardly moves. Accordingly, all parts other than the object OB may be recognized as the background.

Alternatively, when the moving object OB is not captured in the motion image, the same image as the first frame A may continue. In this case, the first frame (A) image may be recognized as a background image. In other words, all parts displayed in the first frame A may be recognized as a background.

As such, it is possible to recognize and extract a portion of the image that does not move during a preset reference frame period as a background.

When the background image similar to the first frame A continues and the object OB is captured by the camera unit 300 , an image similar to the second frame B may be acquired. If the object OB continues to move and leaves the screen, the same image as the first frame A will be acquired again.

When the image before the object OB passes and the image after the object OB passes, the two images may be substantially the same.

As such, even if motion is detected in the image while the object OB moves in the image for a certain period of time, if the image before the object OB is captured and the image after the object OB has passed are almost identical, the corresponding image Most of what you do can be the background.

In other words, even if there is a portion in the image that changes according to movement for a certain period of time, if the image before the change starts and after the change ends are almost the same, the image can be recognized as a background image.

After the background is extracted, the color of the background may be determined and information on the color may be stored.

Thereafter, the color of the background (image serving as the background) and the other motion image may be compared ( S320 ).

The object recognition unit 190 may recognize a part having a color different from the background in the motion image as the moving object OB ( S330 ).

For example, as shown in FIG. 6A , a part having a color different from that of the background, that is, the object OB may be detected.

In addition, after the background and the object OB are separated, the background may be processed as a single color. For example, you can treat the background as black. In this case, the movement of the object OB may be more easily analyzed.

Thereafter, as shown in FIG. 6B , the silhouette of the object OB may be determined. In (B) of FIG. 6 , the red part ER in the upper left corner is too different from the human shape, so it may be treated as an error.

Through this process, it is possible to recognize the moving object (OB) in the motion image.

Thereafter, the motion calculator 200 may analyze the motion of the object OB ( S340 ).

In addition, the mobility may be calculated according to the result of the motion analysis ( S360 ).

In detail, the motion calculator 200 may distinguish the motion of the moving object OB by varying the brightness over time. In addition, the motion calculator 200 may calculate the mobility based on the direction and degree of the change in brightness.

For example, as in the case of FIG. 7 , it is assumed that the object OB, that is, the user raises the left arm.

As shown in FIG. 7 , the user's current appearance may be processed to be relatively bright, and the previous appearance may be processed to be relatively dark.

In this case, it may be determined that the user's left arm moves from the bottom to the top from the dark part to the bright part. That is, the direction of movement can be determined.

In addition, it is possible to determine the movement speed of the left arm according to whether the change in brightness of the left arm is abrupt or gentle.

For example, as shown in (A) of FIG. 8, when the object OB rotates 180° (degrees) about the axis, and as shown in FIG. 8B, the object OB rotates at 90° (degrees) about the axis. ), let's assume that it rotates.

When the change in brightness of (A) and (B) of FIG. 8 is the same, it can be seen that the case of (A) of FIG. 8 has greater mobility than the case of (B), that is, that the movement speed is faster. .

Alternatively, as shown in FIGS. 9A and 9B , it is assumed that the object OB rotates 180° (degrees) about an axis, respectively.

When the change in brightness occurs more rapidly in (B) than in (A) of FIG. 9, in the case of (A) of FIG. 9, the object OB moves 180° (degrees) for a relatively short time. In the case of (B) of FIG. 9 , it may correspond to a case in which the object OB rotates 180° (degrees) for a relatively long time.

Accordingly, the case of (A) of FIG. 9 may have greater mobility than the case of (B).

In this way, it is possible to recognize the moving object OB and calculate the movement of the recognized object OB.

On the other hand, it is possible to use a predetermined mask to detect the motion. For example, a mask of a predetermined size may be applied to a specific region of an image, and a change in luminance of the mask may be sensed to determine motion.

A method of determining exercise information is as follows.

Information on the type of exercise, the exercise action, the number of exercise, the exercise time, etc. described below may be determined based on the information on the motility calculated by the motility calculator 200 .

Referring to FIG. 10 , in the information determination step ( S400 ), at least one of an exercise type, an exercise operation, the number of exercises, an exercise time, an exercise equipment, an exercise route, or a preference may be determined.

A method of determining an exercise motion and/or type is as follows.

Information on a reference motion may be set and stored for each type of exercise. For example, as in the case of FIG. 11 , in the case of push-up exercise, the reference angle Xb between the floor GND and the user H's leg, the reference distance Xa between the upper body and the floor GND, etc. information can be set in advance.

Thereafter, as shown in (A) and (B) of FIG. 12 , when the user performs an exercise, when the camera unit 300 captures an exercise image of the user, the motion determination unit 120 analyzes the exercise image to determine the exercise motion. information can be identified.

The motion determining unit 120 may determine/obtain information about an exercise motion with respect to an angle between the floor and a leg, a distance between an upper body and the floor, and the like.

The type determining unit 110 may compare the motion information obtained by the motion determining unit 120 with information on a preset reference exercise motion.

For example, in (A) of FIG. 12 , the angle between the floor GND and the leg of the user H is the first angle Xb1, and the distance between the upper body and the floor GND is the first distance Xa1 ), it is possible to determine how similar the first angle Xb1 is to a preset reference angle Xb, and to determine how similar the first distance Xa1 is to the reference distance Xa.

If the first angle Xb1 is similar to the reference angle Xb within a predetermined range, and the first distance Xa1 is similar to the reference distance Xa within a predetermined range, ( The same type of exercise as A) can be identified as push-ups.

In this way, it is possible to determine the exercise form of Figure 12 (B) as push-ups.

If the user exercises in the same manner as in the case of FIG. 13, the angle between the floor GND and the leg (the third angle X2) is similar to the preset reference angle Xb within the preset range. Even so, since the upper body of the user H is in contact with the floor GND, the type determining unit 110 may recognize that the exercise is not push-ups.

Here, only the reference distance Xa and the reference angle Xb are described for reference information for convenience of explanation, but the present invention may not be limited thereto. For example, information on the position of the hip, the angle of the knee, the position of the head, the angle of both arms, the position of both hands, etc. may be set as reference information.

The motion determining unit 120 may determine/obtain information about an exercise motion from an exercise image, and may also determine information on exercise accuracy.

The motion determining unit 120 may determine how similar the user's exercise motion is to a preset reference motion. In other words, the motion determining unit 120 can determine how accurate and how good the user H is to exercise in a good form (movement).

For example, as in the case of FIG. 14 , information on the octagonal angle, the degree of bending of the arm, the angle between the floor and the leg, the knee angle, the hip height, etc. in the user's exercise motion is compared with a preset reference motion motion for accuracy, respectively. score can be determined.

In addition, the motion determining unit 120 may calculate a comprehensive evaluation score for the accuracy of the user's exercise compared to the reference exercise motion. That is, it is possible to set a model answer for the exercise motion, and to evaluate the score for the exercise motion of the user.

The items evaluated by the operation determining unit 120 may be variously changed.

For example, in the case of a running exercise, items such as step angle, stride length, arm angle, and upper and lower body movements may be evaluated, and accuracy may be determined according to the evaluation result.

In addition, the motion determining unit 120 may evaluate the difficulty of the user's exercise.

For example, when the user performs an exercise in a form such as (A), (B), (C), (D) or (E) of FIG. 15 , the motion determining unit 120 is shown in FIG. ), (B), (C), (D), and (E) can all be identified as push-ups.

In addition, the operation determining unit 120 determines the difficulty level in the case of FIG. 15A as the first level, and the difficulty level in the case of FIG. 15B is higher than the first level. It is determined as a high second level (Second Level), and the difficulty in the case as in (C) of FIG. 15 is determined as a third level higher than the second level, and in the same case as in (D) of FIG. It is possible to determine the difficulty level as a fourth level higher than the third level, and determine the difficulty level as a fifth level higher than the fourth level as shown in FIG. 15E .

In the above, the case of bare-handed exercise (push-up) has been described, but the above content can also be applied to exercise using a device.

The criterion for determining the accuracy of the operation of the operation determining unit 120 may be set differently for each movement of the bare hand and the movement of the instrument, and it is also possible to be set differently according to the type of the instrument.

As shown in FIG. 16 , when the user H exercises by using a predetermined exercise device 800 , the exercise information processing device 10 in the form of a mobile communication terminal may photograph an exercise image.

In this case, the exercise information processing apparatus 10 may analyze/discriminate the type of exercise and information on the exercise motion according to the above description.

The apparatus determining unit 150 of the exercise information processing device 10 may determine the type of the exercise equipment 800 used by the user H to exercise.

For example, it is possible to store shape information and image information for each exercise equipment in the memory unit 600 and compare it with the exercise equipment shown in the exercise image to determine which type of exercise equipment the user uses. .

Alternatively, it may be possible to assign identification information such as a barcode that can identify the equipment to each exercise equipment, and to use this to determine the exercise equipment.

In addition, when the type of exercise determined by the type determining unit 110 is an exercise using a weight mechanism, the mechanism determining unit 150 may determine a load set in the weight mechanism.

For example, information on the weight, size, shape, etc. of the weight used in each exercise equipment is stored in the memory unit 600 in advance, and compared with the weight used by the user displayed in the exercise image using this information, the total load can be determined.

Alternatively, it is possible to install a strain gauge in the exercise equipment, and to check the load of the equipment using this.

The time determining unit 140 may measure/determine the user's exercise time based on the exercise image.

For example, it is assumed that a result as shown in FIG. 17 is obtained as a result of analyzing a user's exercise image.

Referring to FIG. 17 , in the process of starting the exercise at time T0 and ending the exercise at time Te, the user's mobility may exceed the average value Aa during periods T1-T2, T3-T4, and T5-T6.

In this case, the time determining unit 140 allows the user to exercise during periods T1-T2, T3-T4, and T5-T6, and rest during periods T0-T1, T2-T3, T4-T5 and T6-Te. can be identified as

In this way, the time determining unit 140 may determine information about the user's exercise time as well as information about the rest time.

The above-described exercise type, exercise motion, exercise time, information on exercise equipment, etc. may be processed and provided in a form that can be checked by the user.

For example, as in the case of FIG. 18, when the user performs a bench press exercise, the total exercise time of the exercise, rest time, number of sets, number of exercises for each set, load (weight) for each set, each set Information on exercise time and the like may be provided to the user.

Information on the exercise set may be determined in the same way as in FIG. 17 .

The number of times determining unit 130 may determine the number of times of exercise of the user based on the exercise image.

For example, when the user H performs the push-up exercise as shown in FIG. 19 , the motion of bending and stretching the arm in the prone state may be determined as one push-up exercise. If the user does not bend his arm and maintains the straightened state, it may be determined that no push-up exercise has been performed no matter how long time passes.

It may be preferable that the number of times determining unit 130 counts the number of times when the user's exercise motion matches the preset reference motion by more than a preset reference ratio.

For example, as shown in (A) of Figure 20, in the case of push-up exercise, the reference angle (Xb) between the floor (GND) and the user's (H) leg, the reference distance (Xa) between the upper body and the floor (GND) ) can be set in advance.

Then, when the user performs push-ups as shown in (B) of FIG. 20 , the angle between the floor GND and the user's leg is the third angle Xb3, and the upper body and the floor GND. If the distance between them is the third distance Xa3, it is determined how similar the third angle Xb3 is to the preset reference angle Xb, and to what extent the third distance Xa3 is the reference distance Xa. similarity can be determined.

As a result of the determination, the third angle Xb3 matches the reference motion (reference angle Xb) by more than the reference ratio, and the third distance Xa3 matches the reference operation (reference distance Xa) and the reference operation and the reference ratio or more In the case of matching, it may be determined that the user H has performed one push-up exercise.

If the user exercises in the same manner as in the case of (B) of FIG. 21 , even if the angle Xb4 between the floor GND and the leg matches the reference angle Xb by more than the reference ratio, the user H ), since the distance Xa4 between the upper body and the floor GND does not change, that is, the distance Xa4 between the user H's upper body and the floor GND does not match the reference motion by more than the reference ratio, so It can be determined that the stretching exercise is not performed.

The method of determining the number of exercises may be applied not only to bare-handed exercises such as push-ups, but also to instrument exercises using instruments.

For example, as shown in FIG. 22 , it is assumed that the user H uses the pull-down exercise device 810 .

In this case, while the user (H) raises and lowers his arm, the handle of the pull-down exercise device 810 must move up and down together with the user's arm to determine that the pull-down exercise has been performed once. have.

The information providing unit 210 may provide information on the exercise result to the user.

For example, as in the case of FIG. 23 (A), information about the user's current state (the number of push-ups performed by the user), the average number of push-ups, and the target value for the push-up exercise performed by the user are provided together. it is possible to do

Alternatively, as shown in (B) of FIG. 23 , in the case of a pull-down exercise, it is possible to provide information on a current state (load (weight) of a pull-down exercise performed by a user), an average load, and a target value together.

The case of the bench press exercise is disclosed in (C) of FIG.

The information providing unit 210 may preferably provide information on achievement to the user based on at least one of information on the type of exercise, information on the number of exercises, or information on the exercise time. The achievement may increase as the number of exercise increases and the exercise time decreases.

For example, referring to FIGS. 23A and 24A , in the case of push-up exercise, the user's achievement may be 80% of the average number of times and 67% of the target value.

Achievement information can also be applied to pull-down exercises and bench press exercises.

In addition, the information providing unit 210 may provide recommended information to the user based on at least one of information on the type of exercise, information on the number of exercises, or information on the exercise time. Here, the recommendation information may include at least one of recommendation information on the number of workouts, recommendation information on the workout time, or recommendation information on the type of workout.

For example, as shown in (B) of Figure 24, in the case of push-up exercise, it is recommended to increase the number of executions by 20%, in the case of a pull-down exercise, it is recommended to increase the load by 16%, and in the case of a bench press exercise, it is recommended to increase the number of times by 30 % reduction is recommended. In addition, instead of reducing the number of bench press exercises, it may be recommended to add butterfly exercises. This is because the achievement for the bench frame exercise exceeded 100% as shown in (A) of FIG. 24 .

Alternatively, as shown in (A) of FIG. 25 , in the case of push-up exercise, it is possible to provide the user with recommended information on an exercise motion, such as straightening the knee.

In addition, an example of a desirable push-up operation may be displayed on the display unit 410 as shown in FIG. 25B so that the user can more easily understand.

The provision of recommended information may be applied to an exercise such as yoga, in which the exercise movement itself is considered important, in addition to an exercise related to the number of exercises such as push-ups.

For example, as shown in (A) of 26 , when the user H performs a yoga exercise, the exercise motion information MD may be extracted from the user's exercise image.

In FIG. 26, for convenience of explanation, a movement motion is expressed as a movement of a skeleton as shown in FIG. 26(B), but the present invention may not be limited thereto. For example, even in the case of yoga exercise, the movement may be analyzed/discerned by the object recognition unit 190 and the movement calculating unit 200 described above.

When the user's exercise motion information MD is obtained, as shown in FIG. 26C , the user's exercise motion information MD may be compared with preset reference motion information SD.

As a result of the comparison, the similarity between the user's motion information MD and the reference motion information SD may be determined as an achievement.

For example, as shown in (A) of Figure 27, in the user's yoga exercise, the arm motion is 92% similar to the reference motion information (SD), the leg motion is 95% similar, and the trunk motion is 98% similar. information can be identified. In other words, it can be seen that the user's yoga movement has an accuracy of 92% in the arm movement item.

Based on the information on the accuracy, as shown in (B) of FIG. 27 , it is possible to provide the user with recommendation information for the corresponding exercise.

It may also be possible that the achievement is determined according to the exercise time regardless of the load or the number of times.

For example, as shown in (A) of Figure 28, it is possible to determine / provide the achievement of various exercises, such as bench press exercise, pull-down exercise, push-up exercise, running, etc. for the exercise time.

In addition, as shown in (B) of FIG. 28 , it is possible to provide recommended information to the user based on the achievement of each exercise.

For example, when the exercise time of the user's push-up exercise is less than the average (10 minutes), it is possible to provide the user with recommendation information that tells the user to invest more time in the push-up exercise.

The achievement according to the exercise time may be preferably applied to exercises such as yoga and running.

For example, as shown in FIG. 29(A) , it is assumed that the user H takes a grasshopper posture, a straight posture, a plow posture, and an eagle posture during yoga exercise.

In this case, the user can determine/provide the achievement (100%) by comparing the time (60 seconds) the user takes the grasshopper posture and the posture is maintained with a preset reference time (60 seconds).

In addition, it is possible to provide the user with recommendation information, such as reducing the time for the eagle posture and increasing the practice time for the straight posture and the plow posture, based on the achievement.

Meanwhile, it is possible to provide different recommended information according to difficulty.

For example, as in the case of Figure 30, in the case of push-ups, the case of performing 100 times in 10 minutes is set to level 1, and the case of performing 130 times in 10 minutes is performed at level 2, 160 times in 10 minutes Assume that the case of performing 190 times in level 3 and 10 minutes is set to level 4, and the case of performing 220 times in 10 minutes is set to level 5.

As shown in (A) of Figure 31, if the level 2 user A performs a total of 90 push-ups for 10 minutes and the achievement is 69%, the level is set to level 1 as shown in Figure 31 (B). Downgrade can be recommended.

Alternatively, the exercise information processing apparatus 10 may forcibly lower the level of user A from level 2 to level 1.

On the other hand, as shown in (A) of FIG. 32, when the level 4 user B performs a total of 230 push-ups for 10 minutes and the achievement is 121, as shown in (B) of FIG. It can be recommended to raise the level.

Alternatively, the exercise information processing apparatus 10 may forcibly increase the level of user B from level 4 to level 5 .

The information providing unit 210 may compare various types of information collected from the user with information of other users to provide information on the user's health status.

For example, as in the case of FIG. 33, information such as the user's current muscle strength, muscular endurance, cardiorespiratory endurance, etc. is predicted by analyzing the user's exercise image and comparing the determined/obtained information with big data, and It is possible to provide it to the user.

In the above, the case where the exercise information processing apparatus 10 determines the type of exercise performed by the user from the exercise image has been described. However, unlike this, the exercise information processing apparatus 10 may provide information on the exercise type first. . With reference to the accompanying drawings, it is as follows.

34 to 37 are diagrams for explaining another exercise information processing method according to the present invention. Hereinafter, a description of the parts described in detail above will be omitted. For example, the following contents may be approximately the same as those described above, unless otherwise stated, except that information on the type of exercise and information on the reference motion of the exercise are provided to the user in advance before shooting. .

Referring to FIG. 34 , a step ( S600 ) of providing information on the type of exercise before the step ( S200 ) of photographing may be included.

In this case, it is also possible that the type determining unit 110 is omitted from the control unit 100 .

For example, as in the case of FIGS. 35 to 36 , the exercise information processing device 10 displays information on the type of exercise and information on the reference motion of the exercise to the user before the exercise image is captured on the screen (display unit 410). ) can be provided.

Then, the user can check what kind of exercise he or she currently needs to do.

And the exercise information processing device 10 is to monitor whether the user (H) is performing the corresponding exercise.

This method may be preferably applied to an exercise in which various exercises are performed for each set, such as Crossfit.

For example, as in the case of FIG. 37, a yoga exercise that maintains the braided posture in the first step may be performed.

In this case, as in the case of FIG. 35 , information on the reference motion information of the braided posture may be displayed on the display unit 410 .

In this case, the exercise information processing device 10 may determine the exercise motion for the user's braided posture exercise.

In addition, when the user completes the yoga exercise that maintains the braided leg posture, that is, when the exercise ends, the exercise information processing device 10 performs another exercise, for example, an exercise type and a reference motion for a push-up exercise. information can be provided.

Thereafter, the exercise information processing device 10 may determine the number of times the user exercises for the push-up exercise.

In other words, the exercise information processing device 10 provides information on a reference motion for the first exercise to the user, and determines/ can be obtained

Thereafter, the exercise information processing device 10 further provides information on a reference motion of a second exercise different from the first exercise when the first exercise is ended, and an exercise motion for the second exercise and/or It is possible to determine/obtain information about the number of exercises.

Here, a method of determining whether the exercise is finished is as follows.

The first condition is that the number of exercises for the user's first exercise reaches a preset reference number, and the case where the exercise motion for the user's first exercise matches the reference motion and the preset reference ratio or more Let's assume 2 conditions.

Here, when at least one of the first condition and the second condition is satisfied, it may be determined that the first exercise is ended.

In this way, it is possible to determine/acquire various exercise information during exercise such as CrossFit.

As such, those skilled in the art to which the present invention pertains will understand that the above-described technical configuration of the present invention may be implemented in other specific forms without changing the technical spirit or essential characteristics of the present invention.

Therefore, the embodiments described above are to be understood as illustrative and not restrictive in all respects, and the scope of the present invention is indicated by the following claims rather than the foregoing detailed description, and the meaning and scope of the claims And all changes or modifications derived from the equivalent concept should be construed as being included in the scope of the present invention.

Claims (20)

a camera unit for photographing a user's exercise image;
a type determining unit for determining the type of exercise of the user based on the exercise image;
a motion determining unit for determining the user's motion motion based on the motion image;
an object recognition unit for extracting a background from the motion image and recognizing a part having a color different from the extracted background as a moving object; and
and a mobility calculator for classifying the movement of the moving object by varying the brightness over time, and calculating the mobility based on the direction and degree of the change in the brightness. The method of claim 1,
The apparatus further comprising a time determining unit for measuring the user's exercise time based on the exercise image. 3. The method of claim 2,
The apparatus further comprising an information providing unit for providing recommendation information to the user based on at least one of the information on the exercise type, the information on the exercise motion, and the information on the exercise time. 4. The method of claim 3,
The information providing unit further provides information on achievement to the user based on at least one of the information on the exercise type, the information on the exercise motion, and the information on the exercise time. The method of claim 1,
When the type of exercise is an exercise using a weight mechanism, the apparatus further comprising a mechanism determining unit for determining a load (Load) set in the weight mechanism. The method of claim 1,
The motion determining unit further provides information on the similarity between the user's exercise motion and a preset reference motion. delete delete The method of claim 1,
The type determining unit is a device for determining the type of exercise of the user based on the movement. The method of claim 1,
The motion determining unit determines the user's motion motion based on the motion. taking a user's exercise video;
determining the type of exercise of the user based on the exercise image;
determining an exercise motion of the user based on the exercise image;
a recognition step of extracting a background from the motion image and recognizing a part having a color different from the extracted background as a moving object; and
and classifying the movement of the moving object by varying the brightness according to time, and calculating the mobility based on the direction and degree of the change in the brightness. 12. The method of claim 11,
The method further comprising the step of measuring a user's exercise time based on the exercise image. 13. The method of claim 12,
The method further comprising the step of providing recommendation information to the user based on at least one of the information on the exercise type, the information on the exercise motion, and the information on the exercise time. 13. The method of claim 12,
Further comprising the step of providing information about the achievement to the user,
The information on the achievement is derived based on at least one of the information on the exercise type, the information on the exercise motion, and the information on the exercise time. 12. The method of claim 11,
When the exercise type is an exercise using a weight mechanism, the method further comprising the step of determining a load (Load) set in the weight mechanism. 12. The method of claim 11,
The method further comprising the step of providing information about the similarity (accuracy) between the user's exercise motion and a preset reference motion. delete delete 12. The method of claim 11,
A method of determining the type of exercise of the user based on the movement. 12. The method of claim 11,
A method of determining the exercise motion of the user on the basis of the movement.

Images