Patent Application
20180154215
This application claims priority to and the benefit of Korean Patent Application No. 2016-0163772, filed on Dec. 2, 2016, the disclosure of which is incorporated herein by reference in its entirety.
The present invention relates to a user customized training system and a method of providing a training set thereof.
With the expansion of the environment for sport activities, more people can easily enjoy various sports. Also, as people have recently gained more specialized knowledge regarding sports and living standards have improved, professional personal training has attracted attention.
Professional personal training prevents sport injuries caused by incorrect positions and provides effective exercise effects through personalized training, but has a disadvantage of high cost.
Hence, in order to avoid the disadvantage accompanying the high cost and realize effects of personal training at lower cost, many products which recognize a user's motion using depth cameras or low-cost motion sensors and help the user to self-correct his/her posture have been introduced.
However, since technologies employed in these products merely record a user's motion and compare the user's motion with a predefined correct motion, it is not possible to provide personalized training customized to an individual's characteristics, and hence these products cannot perform a role as personal trainers.
Regarding the above-described technologies, Korean Patent Registration No. 10-1282953 (titled “System and Method for Coaching Sports Motions) discloses a technology for coaching a trainee by transmitting real-time feedback using voice information, video information, and vibrotactile information while allowing the trainee to fix his/her eyes on a target.
An embodiment of the present invention provides a user customized training system and a method of providing a training set which are capable of providing a training set suitable to a user by sensing motion of the user, determining whether the sensed motion is incorrect, and diagnosing athletic performance of the user when the sensed motion is incorrect.
Meanwhile, the technical problems to be solved in the present embodiment are not limited to the above-mentioned technical problems, and there may be other technical problems.
In one general aspect, there is provided a user customized training system including: a sensor module configured to sense a user's motion; a memory in which a program for training is stored; and a processor configured to execute the program stored in the memory, wherein, when the program is executed, the processor acquires coordinates that correspond to the sensed motion, compares the user's motion with pre-stored erroneous motions on the basis of body information generated on the basis of the coordinates, provides a pre-stored set of motion data when a result of the comparison indicates that the user's motion corresponds to an erroneous motion, and, when the sensor module senses a motion of the user corresponding to the set of motion data, provides a training set corresponding to a result of analyzing the sensed motion.
In another general aspect, there is provided a method of providing a training set in a user customized training system, the method including: sensing a user's motion through a sensor module; acquiring coordinates that correspond to the sensed motion; comparing the user's motion with pre-stored erroneous motions on the basis of body information generated on the basis of the coordinates; providing a pre-stored set of motion data when a result of the comparison indicates that the user's motion corresponds to an erroneous motion; sensing a motion of the user corresponding to the set of motion data through the sensor module; and providing a training set corresponding to a result of analyzing the sensed motion.
The above and other objects, features and advantages of the present invention will become more apparent to those of ordinary skill in the art by describing exemplary embodiments thereof in detail with reference to the accompanying drawings, in which:
The present invention will be described more fully hereinafter with reference to the accompanying drawings which show exemplary embodiments of the invention. However, the present invention may be embodied in many different forms and is not to be construed as being limited to the embodiments set forth herein. Also, irrelevant details have been omitted from the drawings for increased clarity and conciseness.
Throughout the detailed description, unless explicitly described otherwise, the word “comprise” and variations thereof such as “comprises” or “comprising” should be understood as implying the inclusion of stated elements and not as excluding any other elements.
The present invention relates to a user-customized training system 100 and a method for providing a training set thereof.
An existing training system provides a training set such that a user's motion or posture is corrected through a comparison with a standardized motion, such as a correct motion of a so-called professional athlete.
However, when a standardized training set is provided, there are problems in that the user may be unable to perform the training set due to physical characteristics of the user or may develop undesired muscles to perform a motion corresponding to the training set.
For example, in the case of squatting, some people may be incapable of performing a squatting motion due to a lack of flexibility. In this case, forcibly following a motion of a professional athlete may increase the risk of injury, and thus a technology for providing a training set suitable to an individual's characteristics is needed.
According to one embodiment of the present invention, it is possible to provide a training set suitable to a user by sensing a motion of the user in various sports, such as golf, baseball, and the like, determining whether the user's motion is incorrect, and diagnosing physical characteristics and athletic performance of the user when the motion is incorrect.
In particular, the present invention is characterized in that a problem in a motion of a user is detected by a primary analysis of a captured motion, and, in order to identify a cause of the problem with the motion, some test sets related to the problematic motion are selected from a plurality of test sets in a customized manner and are then performed by the user such that a secondary analysis to identify the cause of the problem with the motion is conducted.
Hereinafter, a user customized training system 100 according to one embodiment of the present invention will be described with reference to
The user customized training system 100 according to one embodiment of the present invention includes a sensor module 110, a memory 120, a processor 130, and an outputter 140.
The sensor module 110 senses a user's motion. In one embodiment of the present invention, the sensor module 110 may sense the user's motion using one of a depth camera, a stereo camera, a motion sensor, a motion capturing device, and a vision-detection sensor, or through a combination thereof. The sensor module 110 is not necessarily limited to the above mentioned examples, and any device or module is acceptable as long as it is capable of sensing a user's motion.
A program for providing a user customized training set is stored in the memory 120. In this case, the memory 120 collectively refers to non-volatile storage media which retain information even without a supply of power, and volatile storage media.
For example, the memory 120 may include a NAND flash memory, such as a compact flash (CF) card, a secure digital (SD) card, a memory stick, a solid-state drive (SSD), and a micro SD card, a magnetic computer memory device, such as a hard disk drive (HDD), and an optical disc drive, such as a compact disc read-only memory (CD-ROM), a digital versatile disc (DVD)-ROM, and the like.
The processor 130 executes the program stored in the memory 120.
The outputter 140 displays the user's motion or outputs a pre-stored set of motion data through a screen or a voice. In addition, the outputter 140 may output basic training environment information that corresponds to the user's motion through the processor 130.
Such basic training environment information may include a variety of pieces of information depending on the type of exercise. For example, in the case of baseball, the basic training environment information may be a baseball field, positions related to baseball motions, i.e., a batter's box for a batter and a mound for a pitcher, pitches (a breaking ball, a fast ball, etc.), and the presence or absence of a runner, and in the case of skiing, the basic training environment information may be a winter environment, a simulated ski downhill course, etc.
As another example of the basic training environment information, in the case of golf, an environment of a teeing ground may be output when a tee shot is performed, or a screen showing a field may be output when an approach shot is performed.
Specifically, in one embodiment of the present invention, coordinates corresponding to the user's motion sensed by the sensor module 110 are obtained as the processor 130 executes the program stored in the memory 120.
In this case, the processor 130 may obtain joint coordinates of the user as coordinates corresponding to the user's motion. The joint coordinates may be coordinates that correspond to one or more joints of the user's head, shoulders, elbows, hands, waist, knees, and feet.
The processor 130 may generate body information of the user on the basis of the joint coordinates obtained as described above. The body information may be skeleton information generated by connecting the joint coordinates to correspond to a human body.
The processor 130 compares the user's motion with pre-stored erroneous motions on the basis of the generated body information, and when the comparison result shows that the user's motion matches the erroneous motion, the processor 130 provides the user with a pre-stored set of motion data that corresponds to the erroneous motion through the outputter 140.
Such erroneous motion refers to a posture that cannot effectively demonstrate muscular strength or flexibility, for example, a posture possibly causing an injury or an ineffective posture. In this case, the erroneous motion and the set of motion data may be stored in advance in a database formed in the memory 120. In addition, erroneous motions and sets of motion data corresponding to a plurality of kinds of exercise may be classified and stored in advance in the database.
Moreover, when a new kind of exercise is added, a set of motion data corresponding to the added exercise may be added to the database, and the set of motion data may also be edited.
Accordingly, when the user performs a specific motion according to the output set of motion data, the sensor module 110 senses the user's motion that correspond to the set of motion data. In this case, the processor 130 may provide a set of motion data for identifying whether an abnormality occurs in a specific body area of the user to analyze a cause of the occurrence of the user's erroneous motion.
Also, the processor 130 analyzes the user's motion analyzed by the sensor module 110 and controls the outputter 140 to output a training set corresponding to the analysis result.
Meanwhile, the processor 130 may compare the user's motion with the pre-stored erroneous motions or analyze the user's motion corresponding to the set of motion data on the basis of a variation between coordinates acquired at a previous time point and coordinates input at a current time point.
For example, when the coordinate information of the previous time point and the coordinate information of the current time point are sequentially received in units of image frames, the processor 130 determines whether an absolute value of a difference between the coordinates of the previous time point and the coordinates of the current time point is less than or greater than a preset condition, that is, a threshold. When the absolute value does not satisfy the preset condition, it may be determined that the user's motion is an erroneous motion or a motion that does not correspond to the set of motion data.
In addition, the processor 130 may terminate the provision of the training set when a result of analyzing a training time or training accuracy of the user's motion corresponding to the set of motion data is greater than or equal to a reference level.
The analysis result may be stored in the memory 120. After the user's motion is corrected through the training set, an initial motion recognition step is performed such that the user's performance of the corresponding exercise may be re-evaluated.
Meanwhile, the configuration of the user customized training system 100, which includes the sensor module 110, the outputter 140, the memory 120, and the processor 130, according to one embodiment of the present invention may be connected to a network to transmit and receive data, and it should be apparent that the elements may be formed as a single product.
In this case, the network refers to a connection structure in which it is possible to exchange information between nodes, such as terminals and servers, and examples of the network may include a 3rd generation partnership project (3GPP) network, a long term evolution (LTE) network, a world interoperability for microwave access (WIMAX) network, the Internet, a local area network (LAN), a wireless LAN, a wide area network (WAN), a personal area network (PAN), a Bluetooth network, a satellite broadcasting network, an analog broadcasting network, a digital multimedia broadcasting (DMB) network, and the like, but are not limited thereto.
In addition, the user customized training system 100 according to one embodiment of the present invention may be connected to a user terminal 200, such as a smartphone, a tablet personal computer (PC), and the like, through the network. Accordingly, the user terminal 200 may be provided with an analysis result of the user's motion and may display the analysis result.
The user terminal 200 may include, for example, wireless communication devices with guaranteed portability and mobility, i.e., all types of handheld-based wireless communication devices, such as a personal communication system (PCS) terminal, a global system for mobile communication (GSM) terminal, a personal digital cellular (PDC) terminal, a personal handyphone system (PHS) terminal, a personal digital assistant (PDA) terminal, an international mobile telecommunication (IMT)-2000 terminal, a code division multiple access (CDMA)-2000 terminal, a W-code division multiple access (W-CDMA) terminal, a wireless broadband Internet (Wibro) terminal, and the like.
Hereinafter, detailed functions of the user customized training system 100 according to one embodiment of the present invention will be described with reference to a functional block diagram illustrated in
The user customized training system 100 according to one embodiment of the present invention may include a motion sensor module 310, a database 320, a motion data analyzer 330, and an outputter 340 as functional blocks.
The motion sensor module 310 is configured to sense a user's motion, and may be implemented as a motion capturing device or the like which uses a depth camera, an infrared marker, or a motion sensor.
Here, in the case of a depth camera, since a recognition process for each joint is required, a three-dimensional (3D) estimation process may be needed. When the motion sensor module 310 is composed of a depth camera, 3D data is output through the 3D estimation process, and thus it is possible to more accurately sense the user's motion in comparison to a two-dimensional (2D) camera-based training system according to a prior art.
Because the motion capturing device can directly acquire 3D coordinates of each joint, it is possible to utilize position data without a 3D posture estimation process. Erroneous motions and sets of motion data corresponding to a plurality of kinds of exercise are classified and stored in the database 320, and the stored erroneous motions and motion data may be edited by the user. In addition, when a new kind of exercise is added to the database, erroneous motions and a set of motion data corresponding to the added exercise may be also added to the database.
Also, when the motion sensor module 310 is configured with a depth camera, pre-defined learning data for 3D posture estimation may be stored in the database 320.
The motion data analyzer 330 includes a motion recognizer 331, a motion analyzer 333, and a training set provider 335.
The motion recognizer 331 acquires joint coordinates corresponding to the user's motion sensed by the motion sensor module 310. Then, the motion recognizer 331 compares the user's motion to the erroneous motions stored in the database 320 on the basis of the generated joint coordinates and determines whether the user's motion is an erroneous motion.
Specifically, the motion recognizer 331 may determine whether the user's motion corresponds to an erroneous motion by calculating a distance, an angle, and a velocity between the coordinates on the basis of the acquired joint coordinates. Alternatively, the motion recognizer 331 may generate skeleton information by connecting the joint coordinates to correspond to the human body, and determine whether the user's motion corresponds to the pre-stored erroneous motion on the basis of the skeleton information.
The motion recognizer 331 may specifically include a motion interface unit 3331, a motion recognition unit 3313, and an erroneous motion determination unit 3315.
The motion interface unit 3331 is responsible for training the user on a specific exercise, receives a determination result of an erroneous motion, such as a motion that frequently causes an injury during practice, and allows the determination result to be output through the outputter 340.
The motion recognition unit 3313 recognizes a position to be analyzed from previously learned motion data. For example, in the case of golf, the positions to be analyzed may be an address position, a takeaway position, a backswing position, a downswing position, an impact position, a follow-through position, a finish position, and the like. In the case of baseball, the positions to be analyzed may be a takeback position, an impact position, a follow-through position, and the like. As such, the positions to be analyzed may be changed according to a viewpoint adopted in the analysis and may be added or edited.
The erroneous motion determination unit 3315 determines the user's erroneous motion by comparing the user's motion to the erroneous motion pre-stored in the database. In this case, the comparison method may vary according to a predefined method, and various viewpoints of an erroneous position may be applied according to a learning methodology.
The motion analyzer 333 is configured to determine an individual's physical ability by measuring athletic performance, recognizing an exercise posture, and determining the athletic performance. When the motion recognizer 331 determines that the user's motion corresponds to an erroneous motion, the motion analyzer 333 provides a set of motion data stored in the database 320.
The motion analyzer 333 includes an athletic performance measurement interface unit 3331, an exercise posture recognition unit 3333, and an athletic performance diagnosis unit 3335.
The athletic performance measurement interface unit 3331, like other interface units, is connected to the motion sensor module 310 and the outputter 340 and provides the user with a set of motion data for a diagnosis of athletic performance.
The exercise posture recognition unit 3333 recognizes a user's motion corresponding to the set of motion data similarly to the motion recognition unit 3313.
The athletic performance diagnosis unit 3335 measures the overall physical performance of the user through the set of motion data or athletic performance in a particular exercise, such as golf or baseball.
The athletic performance may be diagnosed by requesting that the user perform specific postures corresponding to the set of motion data and then analyzing whether the user quickly, accurately, and repeatedly performs motions.
The training set provider 335 is configured to provide a training set for improving athletic performance according to data for each user analyzed by the motion analyzer 333 and training content for providing a personalized exercise program is stored therein.
To this end, when a motion of the user corresponding to the set of motion data is sensed, the training set provider 335 provides a training set which corresponds to a result of analyzing the user's motion.
Specifically, the training set provider 335 may include a training set providing interface unit 3351 and a training set motion recognition unit 3353.
The outputter 340 displays the user's motion or outputs a pre-stored set of motion data or a training set which corresponds to erroneous motions. In addition, the outputter 340 may output basic training environment information corresponding to the user's motion.
The outputter 340 may individually provide a video output through a large monitor or a projector, a voice output through a speaker, or a vibration output through a wearable device, or may provide a combination thereof.
For example, the outputter 340 may output video data using a projector, voice data, or data through a suit or bracelet having a vibration function.
For reference, each component illustrated in
However, the “components” are not limited to software or hardware components, and each of the components may be configured to reside on an addressable storage medium and be executed by one or more processors.
Thus, a component unit may include, by way of example, a component such as a software component, an object-oriented software component, a class component, and a task component, a process, a function, an attribute, a procedure, a subroutine, a segment of a program code, a driver, firmware, a microcode, circuitry, data, a database, a data structure, a table, an array, and a variable.
Components and functionality provided by the components may be combined into fewer components or further separated into additional components.
Hereinafter, a method of providing a training set in the user customized training system 100 according to one embodiment of the present invention will be described with reference to
In the method of providing a training set according to one embodiment of the present invention, when a user's motion is sensed through a sensor module (S410), coordinates corresponding to the sensed motion are acquired (S420). In this case, the acquired coordinates may be coordinates that correspond to one or more joints of the user's head, shoulders, elbows, hands, waist, knees, and feet.
Meanwhile, in one embodiment of the present invention, the user's motion may be sensed without outputting a screen on the outputter 140, but it may be preferable for basic training environment information corresponding to the user's motion to be output through the outputter 140.
Then, the user's motion is compared with pre-stored erroneous motions on the basis of the acquired coordinates (S430), and when the comparison result indicates that the use's motion corresponds to an erroneous motion (S440), a pre-stored set of motion data for evaluating athletic performance of the user is provided (S450).
Then, when a motion of the user corresponding to the set of motion data is sensed through the sensor module (S460), a training set corresponding to a result of analyzing the sensed motion is provided (S470).
In this case, a training time or training accuracy of the user's motion corresponding to the set of motion data is analyzed, and the analysis result is compared with a reference level. When the analysis result is greater than or equal to the reference level, the provision of the training set may be terminated.
Meanwhile, in the above description, operations S410 to S470 may be further divided into more operations or combined into fewer operations according to embodiments of the present invention. In addition, some of the operations may be omitted when necessary, and the order of the operations may be changed. Further, any omitted descriptions of components or operations described with reference to
According to any of the above-described embodiments of the present invention, unlike an existing motion recognition-based training system which guides standardized exercise positions, a user customized training set can be provided.
In addition, it is possible to determine a position which may cause an injury in a specific exercise due to an incorrect exercise position or insufficient athletic performance and provide a program for diagnosing an individual's athletic performance through an analysis of the incorrect position, thereby making it possible to evaluate the individual's sport performance.
Further, it is possible to enable the user to perform high-level training learning at low cost.
The method of providing a training set in the user customized training system 100 according to one embodiment of the present invention may be implemented in the form of a computer program stored in a medium executed by a computer or a recording medium that includes computer executable instructions. The computer-readable medium may be any usable medium that can be accessed by a computer and may include all volatile and nonvolatile media and detachable and non-detachable media. Also, the computer-readable medium may include all computer storage media and communication media. The computer storage medium includes all volatile and nonvolatile media and detachable and non-detachable media implemented by a certain method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. The communication medium typically includes computer-readable instructions, data structures, program modules, other data of a modulated data signal such as a carrier wave, or other transmission mechanisms, and includes information transmission media.
The method and system of the present invention have been described in connection with specific embodiments of the invention, and some or all of the components or operations thereof may be realized using a computer system that has general-use hardware architecture.
According to any of the above-described embodiments of the present invention, unlike an existing motion recognition-based training system which guides standardized exercise positions, a user customized training set can be provided.
In addition, it is possible to determine a position which may cause an injury in a specific exercise due to an incorrect exercise position or insufficient athletic performance and provide a program for diagnosing an individual's athletic performance through an analysis of the incorrect position, thereby making it possible to evaluate the individual's sport performance.
Further, it is possible to enable the user to perform high-level training learning at low cost.
The above description of the invention is for illustrative purposes, and a person having ordinary skilled in the art should appreciate that other specific modifications can be easily made thereto without departing from the technical spirit or essential features of the invention. Therefore, the foregoing embodiments should be regarded as illustrative rather than limiting in all aspects. For example, each component described as being of a single type can be implemented in a distributed manner. Likewise, components described as being distributed can be implemented in a combined manner.
The scope of the present invention is not defined by the detailed description set forth above but by the accompanying claims of the invention. It should also be understood that all changes or modifications derived from the definitions and scopes of the claims and their equivalents fall within the scope of the invention.
| Number | Date | Country | Kind |
|---|---|---|---|
| 10-2016-0163772 | Dec 2016 | KR | national |
