WO2024075958A1 - Procédé d'évaluation de combat de taekwondo selon un niveau d'entraînement d'utilisateur à l'aide d'une intelligence artificielle - Google Patents

Procédé d'évaluation de combat de taekwondo selon un niveau d'entraînement d'utilisateur à l'aide d'une intelligence artificielle Download PDF

Info

Publication number
WO2024075958A1
WO2024075958A1 PCT/KR2023/011209 KR2023011209W WO2024075958A1 WO 2024075958 A1 WO2024075958 A1 WO 2024075958A1 KR 2023011209 W KR2023011209 W KR 2023011209W WO 2024075958 A1 WO2024075958 A1 WO 2024075958A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
taekwondo
information
sparring
movements
Prior art date
Application number
PCT/KR2023/011209
Other languages
English (en)
Korean (ko)
Inventor
최중구
Original Assignee
주식회사 에이아이태권도
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 에이아이태권도 filed Critical 주식회사 에이아이태권도
Publication of WO2024075958A1 publication Critical patent/WO2024075958A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • A63B71/0605—Decision makers and devices using detection means facilitating arbitration
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
    • A63B24/0003—Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B2220/00—Measuring of physical parameters relating to sporting activity
    • A63B2220/80—Special sensors, transducers or devices therefor
    • A63B2220/806—Video cameras
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B2244/00—Sports without balls
    • A63B2244/10—Combat sports
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20036—Morphological image processing
    • G06T2207/20044—Skeletonization; Medial axis transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30221—Sports video; Sports image

Definitions

  • the present invention relates to a Taekwondo sparring evaluation method and device based on the user's training level using artificial intelligence. More specifically, it relates to a sparring evaluation method and device based on the training level corresponding to the user's skill level using only sparring images without a sensing device. .
  • Taekwondo is a martial art that attacks or defends using hands and feet without weapons, and is a modern traditional martial art characterized by fast and powerful kicking techniques. It was adopted as a demonstration sport at the 1988 Summer Olympics, and was adopted as an official sport starting at the 2000 Summer Olympics.
  • Taekwondo can be largely divided into poomsae (form), sparring (sparring), and breaking (training). Taekwondo, which was adopted as an Olympic sport, is a sparring sport in which the winner and loser are determined by scoring points through striking.
  • the purpose of the present invention to solve the above problems is to provide a method for evaluating Taekwondo sparring according to the user's training level using artificial intelligence.
  • Another purpose of the present invention to solve the above problems is to provide a Taekwondo sparring evaluation device according to the user's training level using artificial intelligence.
  • a Taekwondo sparring evaluation method includes the steps of acquiring image information including a sparring movement of a first user, the image Deriving skeleton information corresponding to the sparring movement of the first user based on information, obtaining first training level information of the first user, and performing a plurality of Taekwondo movements based on the first training level information determining at least one Taekwondo evaluation target motion, determining a Taekwondo execution motion performed by a first user among the plurality of Taekwondo motions based on the skeleton information, and determining the Taekwondo execution motion and the at least one Taekwondo motion. It may include determining whether the first user has performed at least some of the at least one Taekwondo evaluation target movement based on the evaluation target movement.
  • the method may further include determining the number of movements of the first user corresponding to each of the at least one Taekwondo evaluation target movement based on the Taekwondo performance action and the at least one Taekwondo evaluation target action.
  • the technique used by the first user based on the number of movements of the first user corresponding to each of the at least one Taekwondo evaluation target movement and the type information of the movement corresponding to the Taekwondo performance movement among the plurality of Taekwondo movements.
  • a step of determining diversity information may be further included.
  • the image information further includes a sparring movement of a second user who is a sparring opponent of the first user, and a first body region for the first user and a second body region for the second user are determined from the video information. determining whether a strike of the first user to the second user is effective based on the first body region, the second body region, and the skeleton information; among the plurality of Taekwondo movements, the Determining a hitting motion corresponding to the sparring movement of the first user at the time when the hitting is determined to be effective based on skeleton information, first body information of the first user and second body information of the second user Obtaining, correcting the hitting motion based on the first body information and the second body information, and the corrected hitting motion and the sparring movement of the first user at the time when the hitting is determined to be effective. It may further include determining the first user's evaluation value for the hitting motion based on the hitting motion.
  • An electronic device that performs a Taekwondo sparring evaluation method according to a user's training level according to an embodiment of the present invention for achieving the above other object includes a processor and a memory that stores at least one command executed by the processor. memory), wherein the at least one command is executed to obtain image information including the sparring movement of the first user, and to derive skeleton information corresponding to the sparring movement of the first user based on the image information.
  • the Taekwondo movement performed by the first user is determined, and the first user performs the at least one Taekwondo movement based on the Taekwondo movement and the at least one Taekwondo evaluation target movement. It may be executed to determine whether at least some of the movements subject to Taekwondo evaluation have been performed.
  • sparring evaluation can be conducted without players using equipment with separate sensors attached.
  • the possibility of misjudgment due to malfunction of the sensor can be prevented.
  • the user's training level (level, poom, dan, etc.) can be viewed only through images: how many times the movements that must be performed in a sparring match were performed, how accurately they were performed, what the degree of attack and defense was, and how many different techniques were used. You can see overall whether it has been used.
  • the effects are not limited to the effects described above, and effects not mentioned can be clearly understood by those skilled in the art from this specification and the attached drawings. .
  • FIG. 1 is a block diagram of an electronic device that performs a Taekwondo sparring evaluation method according to the user training level using artificial intelligence according to an embodiment of the present invention.
  • Figure 2 is a conceptual diagram illustrating a method for evaluating Taekwondo sparring according to the user training level using artificial intelligence according to an embodiment of the present invention.
  • Figure 3 is a flow chart of a Taekwondo sparring evaluation method according to the user training level using artificial intelligence according to an embodiment of the present invention.
  • Figure 4 is a diagram showing key points used to recognize a user's movement from an image according to an embodiment of the present invention.
  • Figure 5 is a diagram for explaining a configuration in which Taekwondo evaluation target movements are determined according to the training level according to an embodiment of the present invention.
  • Figure 6 is a diagram illustrating a configuration in which the number of user movements for each Taekwondo evaluation target movement is counted according to an embodiment of the present invention.
  • Figure 7 is a diagram illustrating a configuration for correcting a movement subject to Taekwondo evaluation based on the other person's body information according to an embodiment of the present invention.
  • first, second, A, B, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.
  • a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention.
  • the term “and/or” includes any of a plurality of related stated items or a combination of a plurality of related stated items.
  • FIG. 1 is a block diagram of an electronic device that performs a Taekwondo sparring evaluation method according to the user training level using artificial intelligence according to an embodiment of the present invention.
  • an electronic device 100 that performs a Taekwondo sparring evaluation method according to the user training level using artificial intelligence according to an embodiment of the present invention includes at least one processor 110, a memory 120, and a transmission/reception device. It may be configured to include a device 130. Additionally, the electronic device 100 may further include at least one of an input interface device 140, an output interface device 150, and a storage device 160.
  • the at least one processor 110 may be a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. It can mean.
  • Each of the memory 120 and the storage device 160 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium.
  • the memory 120 may be one of read only memory (ROM) and random access memory (RAM), and the storage device 160 may be flash memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).
  • the transceiver 130 can communicate through a wireless network, and each component included in the electronic device 100 is connected by a bus 170 to communicate with each other. can do.
  • the memory 120 may store at least one instruction performed by the processor 110, and the at least one instruction may be used in a Taekwondo sparring evaluation method according to the user training level using artificial intelligence, which will be described later. It can be executed to perform at least some action.
  • Figure 2 is a conceptual diagram illustrating a method for evaluating Taekwondo sparring according to the user training level using artificial intelligence according to an embodiment of the present invention.
  • the electronic device 100 that performs a Taekwondo sparring evaluation method according to the user training level using artificial intelligence is configured to evaluate the sparring movements of the first user and/or the sparring of the first user.
  • Image information including the sparring movements of the second user, the opponent, can be acquired, and the sparring movements can be analyzed and evaluated based on the acquired video information.
  • the electronic device 100 may represent at least one server.
  • the electronic device 100 may be referred to as a Taekwondo sparring evaluation server.
  • the electronic device 100 may perform a Taekwondo sparring evaluation method by transmitting and receiving information with the user terminal 200 through wired or wireless communication.
  • the user terminal 200 may be a communication capable desktop computer, laptop computer, laptop, smart phone, tablet PC, or mobile phone. ), smart watch, smart glass, digital camera, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc. , but is not limited thereto, and may include all electronic devices capable of computing.
  • wireless communications include LTE, LTE Advance (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), Wireless Broadband (WiBro), and Global System for GSM (GSM).
  • Mobile Communications wireless fidelity (WiFi), Bluetooth, Bluetooth Low Energy (BLE), Zigbee, near field communication (NFC), Magnetic Secure Transmission, Radio Frequency (RF), or body area network (BAN), etc., but is not limited thereto.
  • the wired communication may include at least one of universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), power line communication, or plain old telephone service (POTS).
  • USB universal serial bus
  • HDMI high definition multimedia interface
  • RS-232 recommended standard 232
  • POTS plain old telephone service
  • the user terminal 200 may analyze and evaluate Taekwondo sparring actions based on image information acquired by itself without transmitting or receiving information to or from the electronic device 100.
  • analysis and evaluation may be performed in the user terminal 200 itself, and after the electronic device 100 acquires image information from the user terminal 200, analysis and evaluation are performed. is performed, and result information may be provided to the user terminal 200.
  • Figure 3 is a flow chart of a Taekwondo sparring evaluation method according to the user training level using artificial intelligence according to an embodiment of the present invention.
  • image information including the sparring movement of the first user.
  • image information may represent information about a moving image or a plurality of still images.
  • the image information may include a plurality of image information acquired at different times, and the plurality of image information may be arranged in chronological order.
  • the video information may include information about at least a portion of the video from the start to the end of the sparring match or evaluation.
  • one embodiment may derive skeleton information corresponding to the sparring movement of the first user based on image information.
  • the configuration of deriving skeleton information corresponding to sparring movements will be explained in more detail with Figure 4.
  • Figure 4 is a diagram showing key points used to recognize a user's movement from an image according to an embodiment of the present invention.
  • skeleton information may be derived using a skeleton extraction model previously learned from Taekwondo movements.
  • the skeleton information may include a plurality of key points and information about the line between the two key points. For example, there may be 30 key points, and each key point may be named from 0 to 30.
  • key point 0 may represent a part corresponding to the nose (or philtrum)
  • key point 1 may indicate a part corresponding to the left ear (or temple).
  • Key point number 2 may represent the corresponding part corresponding to the left eye
  • key point number 3 may represent the portion corresponding to the right eye
  • key point number 4 may represent the portion corresponding to the right ear (or temple).
  • Key point number 5 may represent the part corresponding to the tip of the chin
  • key point number 6 may represent the part corresponding to the center of the neck or the ulna bone.
  • Key point number 7 may represent a part corresponding to the left shoulder.
  • Key point number 8 may represent the part corresponding to the left elbow.
  • Key point number 9 may represent a part corresponding to the left wrist,
  • key point number 10 may indicate a part corresponding to the tip of the left thumb, and
  • key point number 11 may indicate a part corresponding to the tip of the left middle finger.
  • Key point 12 may represent a part corresponding to the right shoulder
  • key point 13 may indicate a part corresponding to the right elbow
  • key point 14 may indicate a part corresponding to the right wrist
  • Key point number 15 may represent the part corresponding to the tip of the right thumb
  • key point number 16 may indicate the part corresponding to the tip of the right middle finger.
  • Key point number 17 may represent the part corresponding to the center of the chest (or solar plexus), and key point number 18 may represent the part corresponding to the center of the waist (or danjeon).
  • Key point 19 may represent the part corresponding to the center of the left pelvis (or hip), key point 20 may indicate the part corresponding to the left knee, and key point 21 may represent the part corresponding to the left ankle. It can be expressed.
  • Key point number 22 may represent the part corresponding to the heel of the left foot, key point number 23 may represent the part corresponding to the tip of the left big toe, and key point number 24 may represent the part corresponding to the tip of the left little toe. .
  • Key point number 25 may represent the part corresponding to the center of the right pelvis (or buttocks).
  • Key point No. 26 may represent a portion corresponding to the right knee
  • key point No. 27 may represent a portion corresponding to the right ankle
  • key point No. 28 may represent a portion corresponding to the heel of the right foot.
  • Key point number 29 may represent the part corresponding to the tip of the right big toe
  • key point number 30 may represent the part corresponding to the tip of the right little toe.
  • the key point may be expressed as an edge.
  • information about a specific key point may include at least one of the part indicated by the specific key point, movement information of the specific key point, and location information of the specific key point in the image.
  • the skeleton extraction model can be learned through machine learning by configuring training image information about motion and learning skeleton information corresponding to the learning image information into a learning data set, and the algorithm used for machine learning is DNN (deep neural network).
  • DNN deep neural network
  • network Convolutional Neural Network
  • RNN Recurrent Neural Network
  • RBM Restricted Boltzmann Machine
  • DBN Deep Belief Network
  • one embodiment may obtain first training level information of the first user, and in operation S340, one embodiment may perform a plurality of Taekwondo movements based on the first training level information. At least one movement subject to Taekwondo evaluation can be determined. The configuration that determines the movements subject to Taekwondo evaluation according to the level of training will be explained in more detail with Figure 5.
  • Figure 5 is a diagram for explaining a configuration in which Taekwondo evaluation target movements are determined according to the training level according to an embodiment of the present invention.
  • Taekwondo evaluation target movements may be preset according to each training level.
  • the training level may represent one of grade, rank, and dan, but is not limited to these.
  • the movements subject to Taekwondo evaluation when the trainee is a 1st class and the movements subject to Taekwondo evaluation when the trainee is a 2nd class may all be different from each other, or only some of them may be different and the rest may be the same. This may vary depending on promotion regulations, promotion regulations, promotion regulations, or user settings.
  • the first user is 2nd class
  • he/she must perform at least some of the Taekwondo evaluation target movements corresponding to 2nd class during a sparring match, and evaluation can be made accordingly.
  • one embodiment may determine a Taekwondo performance performed by the first user among a plurality of Taekwondo movements based on skeleton information. That is, one embodiment may determine or determine which of several Taekwondo movements the first user performed based on skeleton information.
  • One embodiment may compare skeleton information corresponding to the sparring movement of the first user with a plurality of skeleton information corresponding to a plurality of preset Taekwondo movements to determine the Taekwondo movement performed by the user, and the skeleton information of the first user may be compared.
  • the similarity between the information and the plurality of skeleton information can be derived, and the Taekwondo movement corresponding to the skeleton information with the highest similarity among the plurality of skeleton information can be derived and determined as the Taekwondo movement performed by the user.
  • an embodiment may determine whether the first user has performed at least some of the at least one Taekwondo evaluation target movement based on the Taekwondo performance action and the at least one Taekwondo evaluation target action. That is, in one embodiment, in order to evaluate the movement corresponding to the training level of the first user, it may be determined whether the Taekwondo performance movement of the first user is included in the Taekwondo evaluation target movement corresponding to the first user's training level.
  • Figure 6 is a diagram illustrating a configuration in which the number of user movements for each Taekwondo evaluation target movement is counted according to an embodiment of the present invention.
  • a first evaluation is performed for each of the at least one Taekwondo evaluation target movement corresponding to the training level. It is possible to count how many times the user has performed the game, and when the sparring match is over, the number of movements of the first user for each movement subject to Taekwondo evaluation during the sparring game can be determined and provided.
  • the first user's technique diversity information may be determined based on the number of movements of the first user for each of the taekwondo evaluation target movements.
  • the first user's usage technique diversity information is based on the number of movements of the first user for each of the Taekwondo evaluation target movements and the type information of movements that are not Taekwondo evaluation target movements among the plurality of Taekwondo movements. can also be judged.
  • the number of movements of the first user for each of the Taekwondo evaluation target movements of the first user and the type information and number of movements for each type of movements that are not Taekwondo evaluation target movements among a plurality of Taekwondo movements may be performed by the first user. You can also determine the technology diversity information used.
  • the technology diversity information used may include a technology diversity score.
  • the technical diversity score may be judged higher as the number of types of movements performed by the user increases, and may be judged higher as the difference in the number of times for each movement is small.
  • the technology diversity information in use may be determined only by the Taekwondo evaluation target motion, but in terms of technology utilization, the usage technology diversity information may be determined by considering not only the Taekwondo evaluation target motion but also a plurality of Taekwondo movements.
  • one embodiment may determine attack/defense ratio information based on the Taekwondo performance performed by the first user. For example, in one embodiment, the number of attack movements of the first user and the number of defense movements of the first user are determined based on information on the type of movement corresponding to the Taekwondo performance performed by the first user among a plurality of Taekwondo movements. It can be calculated and judged, and information on the attack/defense ratio of the first user in a sparring match can be determined and provided based on the number of attack moves and the number of defense moves.
  • Figure 7 is a diagram illustrating a configuration for correcting a movement subject to Taekwondo evaluation based on the other person's body information according to an embodiment of the present invention.
  • a variable standard considering body information may be used rather than a single standard.
  • one embodiment may obtain first body information of the first user and second body information of the second user who is the target of the first user's competition, The height of the correct blow can be adjusted based on the first body information and the second body information. In other words, in one embodiment, it may be determined whether the first user accurately performed an action toward the height of a specific part considering the height of the second user using body information including height information.
  • the user's body information may include at least one of the user's height information, weight information, and body shape information, and the body shape information may include at least one of upper body length information, lower body length information, and upper and lower body ratio information.
  • the user's body information may include skeletal information. Skeleton information may include length information and head circumference information of the skeleton corresponding to a specific part of the body.
  • one embodiment when evaluating only effective striking movements, one embodiment includes both the sparring movements of the first user and the sparring movements of the second user, who is the first user's sparring opponent, in order to determine whether the hitting is effective.
  • image information may be obtained, and a first body area for the first user and a second body area for the second user may be determined from the image information, based on the first body area, the second body area, and the skeleton information. It is possible to determine whether the first user's blow to the second user is effective.
  • the body area may be determined based on the outline or body shape of the user's body in image information. Information about body areas can be used to determine whether the bodies of users are touching or hitting each other.
  • the key point corresponding to the touched region among the plurality of key points of the skeleton information is used as the attack key point. You can decide. Then, in one embodiment, it may be determined whether the attack key point is included in the effective key point corresponding to the body part where the attack is effective among the plurality of key points, and if the attack key point is included in the valid key point, the attack key point can be determined as the hitting key point, and in this case, the hitting can be determined to be effective.
  • key point number 19 is not a body part where an attack is effective. It is not included in the valid key points, and accordingly, key point number 19 may not be determined as a hitting key point even if it touches the second body area of the second user.
  • key point number 29 is a body part where the attack is effective, so it is included in the effective key point. Accordingly, key point number 29 that touches the second body area of the second user may be determined as the hitting key point.
  • a striking motion corresponding to the sparring movement of the first user at the time the striking is determined to be effective may be determined based on skeleton information among a plurality of Taekwondo movements, and the first user
  • the first body information of the user and the second body information of the second user may be obtained, and the striking motion may be corrected based on the obtained first body information and the second body information.
  • the hitting height of the Taekwondo action (hitting action) corresponding to the action of hitting the second user can be corrected based on the second user's body information.
  • the hitting motion corrected as described above may represent the optimal motion in the current situation of the first user in which the first body information of the first user and the second body information of the second user are reflected, and the hitting motion corrected in this way
  • the first user's evaluation value for the hitting motion may be determined based on the first user's sparring movement at the time when the hitting is determined to be effective.
  • the evaluation value is based on the location information of a plurality of key points corresponding to the corrected striking motion and the plurality of key point location information of the skeleton information corresponding to the sparring movement of the first user at the time when the hitting is judged to be effective. It can be derived as: Alternatively, the evaluation value is calculated by calculating the position difference information of the same part based on the corrected hitting motion and the plurality of key point position information of the first user's sparring movement at the time when the hitting is judged to be effective, and then evaluating the evaluation value based on this. can also be derived.
  • the evaluation value may represent an evaluation value regarding accuracy.
  • one embodiment may determine proficiency information of the first user.
  • the skill information may include at least one of distance control information, strength information, and movement continuity information.
  • skill information may be determined according to different ratios or weights between distance control information, force intensity information, and motion continuity information, but may also be determined at the same ratio or weight. These ratios or weights may vary depending on settings and may change automatically depending on the level of training.
  • weights for each evaluation item may be set differently depending on the training level of the first user.
  • the distance control information may be obtained based on information on the optimal distance to the other person for the action. For example, in one embodiment, when the Taekwondo performance movement of the first user is determined, reference distance information with a preset sparring opponent corresponding to the Taekwondo performance movement may be obtained, and the first user's first body information and Based on the second body information of the second user, the sparring opponent, the reference distance information can be corrected to match the actual bodies of the sparring subjects.
  • movement performance distance information between the first user and the second user at the time when the first user determines the Taekwondo performance movement may be derived through image information, and the derived movement performance distance information and the corrected reference distance Based on the information, distance adjustment information regarding whether the first user performed the operation at an appropriate distance may be determined. For example, the distance adjustment information may be determined based on the differences between the operation performance distance information and the corrected reference distance information for each of the operations performed by the user, but is not limited to this.
  • Information on strength and weakness can be obtained based on how much force is applied to the first user's blow, that is, the intensity of the blow.
  • time-dependent location information of a key point corresponding to the hit key point among a plurality of key points can be obtained through image information
  • Acceleration information of the hitting key point can be derived based on the location information.
  • the intensity of the blow may be determined based on the first body information and acceleration information of the first user, and strength information may be determined based on the intensity of the blow for each blow.
  • Movement continuity information may indicate whether the first user used several Taekwondo movements consecutively. For example, in one embodiment, temporal difference information between the points in time when the first user's Taekwondo performance movement is determined may be derived, and movement continuity information may be determined based on this. For example, if the difference in time between the first Taekwondo performance action and the next second Taekwondo performance action is less than or equal to the critical time, the first Taekwondo performance action and the second Taekwondo performance action may be determined to be continuous actions, and the continuous action Operations determined as can be clustered into one continuous operation.
  • continuity information of motion may be determined based on the number of clustered continuous motions and the number of motions within the continuous motion consisting of the largest number of motions among the clustered continuous motions, but the present invention is not limited thereto.
  • one embodiment may determine expressiveness information of the first user.
  • the expressiveness information may include at least one of spirit information and creative technology information.
  • expressiveness information may be determined according to different ratios or weights between spirit information and creative technology information, but may also be determined at the same ratio or weight. These ratios or weights may vary depending on settings and may change automatically depending on the level of training.
  • audio information corresponding to image information may be acquired, and audio information at the time of action corresponding to the time when the first user's Taekwondo performance movement is determined or the time when the strike is determined to be effective may be derived from the audio information.
  • the time when the first user's Taekwondo performance movement is determined or the time when the strike is determined to be effective may be referred to as the audio extraction reference time.
  • the operation time audio information may include audio information from a start point located before the audio extraction reference point to an end point located after the audio extraction reference point, and the first temporal difference between the audio extraction reference point and the start point. and a second temporal difference between the audio extraction reference point and the end point, respectively, may be preset and may be different from each other.
  • One embodiment may determine spirit information based on audio information at the time of operation.
  • the creative technique information may represent information about the first user's creative sparring movements rather than a plurality of preset Taekwondo movements.
  • Creative technology information can be obtained through an evaluator terminal connected in advance through a network, and the evaluator terminal can transmit creative technology information including the creative technology score entered by the evaluator.
  • the comprehensive evaluation information may include a comprehensive evaluation value and may be determined based on at least one of accuracy information, proficiency information, expressiveness information, skill diversity information, and attack/defense information, and each piece of information is referred to as an evaluation item. It can be expressed.
  • the accuracy information may include an evaluation value regarding accuracy
  • the technology diversity information may include the technology diversity information used
  • the attack/defense information may include attack/defense ratio information.
  • weights for each evaluation item may be set differently depending on the training level of the first user. For example, when the first user is ranked 1st, the ratio of accuracy information in the comprehensive evaluation information may be different from the rate occupied by the accuracy information in the comprehensive evaluation information when the first user is ranked 2nd. In other words, some items may have the same ratio or weight depending on the training level of the first user, but the ratio or weight may be set differently for all items.
  • one embodiment may provide the determined comprehensive evaluation information of the first user to the user terminal or another terminal connected through a network.
  • the comprehensive evaluation value included in the comprehensive evaluation information is greater than or equal to the passing threshold, the first user's sparring evaluation result may be judged as passing, and the current training level is raised one level to increase the first user's training level. It can be updated.
  • Computer-readable recording media include all types of recording devices that store data that can be read by a computer system. Additionally, computer-readable recording media can be distributed across networked computer systems so that computer-readable programs or codes can be stored and executed in a distributed manner.
  • modules processes, functions, etc.
  • Modules are stored in memory and can be executed by a processor.
  • Memory may be internal or external to the processor and may be connected to the processor by a variety of well-known means.
  • computer-readable recording media may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, etc.
  • Program instructions may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter, etc.
  • a block or device corresponds to a method step or feature of a method step.
  • aspects described in the context of a method may also be represented by corresponding blocks or items or features of a corresponding device.
  • Some or all of the method steps may be performed by (or using) a hardware device, such as a microprocessor, programmable computer, or electronic circuit, for example. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.
  • a programmable logic device e.g., a field programmable gate array
  • a field programmable gate array may operate in conjunction with a microprocessor to perform one of the methods described herein. In general, the methods are preferably performed by some hardware device.

Landscapes

  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physical Education & Sports Medicine (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

Un mode de réalisation de la présente invention concerne un procédé d'évaluation de combat de Taekwondo selon un niveau d'entraînement d'utilisateur, effectué par au moins un serveur, le procédé étant caractérisé en ce qu'il comprend les étapes consistant à : obtenir des informations d'image comprenant des mouvements de combat d'un premier utilisateur ; dériver des informations de squelette correspondant aux mouvements de combat d'un premier utilisateur sur la base des informations d'image ; obtenir des premières informations de niveau d'entraînement du premier utilisateur ; déterminer au moins une action cible d'évaluation de Taekwondo parmi une pluralité d'actions de Taekwondo sur la base des premières informations de niveau d'entraînement ; déterminer une action de Taekwondo effectuée qui est effectuée par le premier utilisateur parmi la pluralité d'actions de Taekwondo sur la base des informations de squelette ; et déterminer si le premier utilisateur a effectué au moins une partie de ladite au moins une action cible d'évaluation de Taekwondo sur la base de l'action de Taekwondo effectuée et de ladite au moins une action cible d'évaluation de Taekwondo.
PCT/KR2023/011209 2022-10-07 2023-08-01 Procédé d'évaluation de combat de taekwondo selon un niveau d'entraînement d'utilisateur à l'aide d'une intelligence artificielle WO2024075958A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2022-0128751 2022-10-07
KR1020220128751A KR102510014B1 (ko) 2022-10-07 2022-10-07 인공지능을 이용한 사용자 수련 수준에 따른 태권도 겨루기 평가 방법

Publications (1)

Publication Number Publication Date
WO2024075958A1 true WO2024075958A1 (fr) 2024-04-11

Family

ID=85512182

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2023/011209 WO2024075958A1 (fr) 2022-10-07 2023-08-01 Procédé d'évaluation de combat de taekwondo selon un niveau d'entraînement d'utilisateur à l'aide d'une intelligence artificielle

Country Status (2)

Country Link
KR (2) KR102510014B1 (fr)
WO (1) WO2024075958A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102510014B1 (ko) * 2022-10-07 2023-03-15 주식회사 에이아이태권도 인공지능을 이용한 사용자 수련 수준에 따른 태권도 겨루기 평가 방법
KR102619792B1 (ko) * 2023-05-19 2024-01-03 주식회사 에이아이비즈 영상 정보를 활용한 격투기 인공지능 판정 시스템 및 방법
KR102670939B1 (ko) * 2023-07-12 2024-06-03 주식회사 에이아이비즈 센서 데이터를 활용한 운동 자세 평가 시스템 및 방법

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120143358A1 (en) * 2009-10-27 2012-06-07 Harmonix Music Systems, Inc. Movement based recognition and evaluation
KR20160043297A (ko) * 2014-10-13 2016-04-21 주식회사 진스튜디오 키넥트 센서를 이용한 실시간 태권도 동작 분석 장치 및 방법
KR20160100753A (ko) * 2015-02-16 2016-08-24 (주)콘텐츠비젼 동작 인식을 통한 태권도 품새 평가 시스템 및 방법
KR20170119338A (ko) * 2016-04-18 2017-10-27 (주)아이들 운동정보 처리 장치 및 방법
KR102510014B1 (ko) * 2022-10-07 2023-03-15 주식회사 에이아이태권도 인공지능을 이용한 사용자 수련 수준에 따른 태권도 겨루기 평가 방법

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102381907B1 (ko) * 2021-09-23 2022-04-04 최중구 태권도 동작에 대한 커리큘럼 기반의 학습 보조 방법 및 장치

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120143358A1 (en) * 2009-10-27 2012-06-07 Harmonix Music Systems, Inc. Movement based recognition and evaluation
KR20160043297A (ko) * 2014-10-13 2016-04-21 주식회사 진스튜디오 키넥트 센서를 이용한 실시간 태권도 동작 분석 장치 및 방법
KR20160100753A (ko) * 2015-02-16 2016-08-24 (주)콘텐츠비젼 동작 인식을 통한 태권도 품새 평가 시스템 및 방법
KR20170119338A (ko) * 2016-04-18 2017-10-27 (주)아이들 운동정보 처리 장치 및 방법
KR102510014B1 (ko) * 2022-10-07 2023-03-15 주식회사 에이아이태권도 인공지능을 이용한 사용자 수련 수준에 따른 태권도 겨루기 평가 방법

Also Published As

Publication number Publication date
KR102510014B1 (ko) 2023-03-15
KR20240049129A (ko) 2024-04-16

Similar Documents

Publication Publication Date Title
WO2024075958A1 (fr) Procédé d'évaluation de combat de taekwondo selon un niveau d'entraînement d'utilisateur à l'aide d'une intelligence artificielle
US11642047B2 (en) Interactive training of body-eye coordination and reaction times using multiple mobile device cameras
Mortazavi et al. Determining the single best axis for exercise repetition recognition and counting on smartwatches
AU2017331639B2 (en) A system and method to analyze and improve sports performance using monitoring devices
KR102486337B1 (ko) 인공지능을 이용한 태권도 겨루기에서의 타격 수치 결정 방법 및 장치
US10769796B2 (en) Information processing apparatus, information processing method and recording medium
US20190366154A1 (en) Physical activity training assistant
CN109731302A (zh) 运动姿态识别方法、装置及电子设备
Fan et al. Sensor fusion basketball shooting posture recognition system based on CNN
US10272292B1 (en) Adaptive sport posture sensing system and method
US11547904B2 (en) Exercise assisting device and exercise assisting method
CN111957047A (zh) 关卡配置数据调整方法、计算机设备及存储介质
US20230077273A1 (en) Method and apparatus for assisting exercise posture correction using working muscle information depending on motion
US20210060385A1 (en) Advancement Manager In A Handheld User Device
WO2018093216A1 (fr) Dispositif et procédé de reconnaissance de type d'exercice
KR102095647B1 (ko) 스마트기기를 이용한 동작 비교장치 및 동작 비교장치를 통한 댄스 비교방법
CN113111683B (zh) 发球违例姿态识别平台及方法
Huang et al. Analysis Technology of Tennis Sports Match Based on Data Mining and Image Feature Retrieval
KR102630828B1 (ko) 인공지능을 이용한 태권도 단체 품새 동작 평가 방법 및 장치
CN117222455A (zh) 用于单个运动员和团队模拟的系统和方法
CN114842372A (zh) 接触式犯规检测方法、装置、电子设备和存储介质
CN112587904A (zh) 学生健康促进监测系统和学生健康促进方法
US20130225294A1 (en) Detecting illegal moves in a game using inertial sensors
WO2022191680A1 (fr) Dispositif et procédé d'analyse de courses de queue de billard
KR102377754B1 (ko) 오토코칭정보 제공방법 및 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23875028

Country of ref document: EP

Kind code of ref document: A1