WO2018097621A1 - Système et procédé d'analyse de marche, et support d'enregistrement lisible par ordinateur - Google Patents

Système et procédé d'analyse de marche, et support d'enregistrement lisible par ordinateur Download PDF

Info

Publication number
WO2018097621A1
WO2018097621A1 PCT/KR2017/013423 KR2017013423W WO2018097621A1 WO 2018097621 A1 WO2018097621 A1 WO 2018097621A1 KR 2017013423 W KR2017013423 W KR 2017013423W WO 2018097621 A1 WO2018097621 A1 WO 2018097621A1
Authority
WO
WIPO (PCT)
Prior art keywords
walking
joint angle
inertial measurement
severity
pedestrian
Prior art date
Application number
PCT/KR2017/013423
Other languages
English (en)
Korean (ko)
Inventor
조재성
김영국
Original Assignee
알바이오텍 주식회사
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 알바이오텍 주식회사 filed Critical 알바이오텍 주식회사
Publication of WO2018097621A1 publication Critical patent/WO2018097621A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/112—Gait analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches

Definitions

  • the present invention relates to a gait analysis system, a method, and a computer-readable recording medium, and more specifically, to determine whether a pedestrian's knee disease and severity from joint angle data obtained by using an inertial measurement apparatus attached to a pedestrian body, A gait analysis system, a method for generating a model capable of determining the same, and a computer readable recording medium.
  • a method of determining a walking pattern of a pedestrian using an inertial sensor attached to a pedestrian body is used, and it is possible to measure or analyze damage to a joint through this method.
  • An object of the present invention is to provide a gait analysis system, a method and a computer-readable recording medium that can generate a meaningful model that can determine the severity of the knee disease through machine learning about the joint angle information of pedestrians.
  • the step of measuring the lower limb joint angle of the pedestrian through the inertial measurement device attached to the body of the pedestrian, gait event using the gyroscope data obtained through the inertial measurement device Extracting a step, detecting a walking step from the walking event, subdividing the joint angle into the walking step, and performing machine learning on the joint angle subdivided into the walking step to perform a plurality of groups according to data characteristics. And classifying the severity of the knee disease for the plurality of groups.
  • the inertial measurement device may include a three-axis acceleration sensor, three-axis gyro sensor and geomagnetic field sensor.
  • a parameter for determining the knee disease may be selected.
  • the gait event is time information on a gait cycle
  • the gait step includes a stance phase and a swing phase, or an initial support step and a terminal support step. It may include.
  • a computer-readable recording medium may be provided in which a program for executing the gait analysis method according to the present invention is recorded.
  • the inertial measurement device is attached to the pedestrian body to measure the joint angle of the lower limbs of the pedestrian, the gait event using the gyroscope data obtained through the inertial measurement device
  • a gait event extractor to extract a gait step from the gait event
  • a gait step detector to subdivide the joint angle into the gait steps, and perform a machine learning on the joint angles segmented by the gait steps to provide data characteristics.
  • a clustering unit classifying the plurality of groups and a determination unit to determine the severity of the knee disease for the plurality of groups.
  • the inertial measurement device may include a three-axis acceleration sensor, three-axis gyro sensor and geomagnetic field sensor.
  • the determination unit may determine the severity by comparing the relative distance in the joint step information of the normal walking step and the joint angle information corresponding to each of the plurality of groups classified by the clustering unit in space.
  • the determination unit may select a parameter for determining the knee disease.
  • the gait event is time information on a gait cycle
  • the gait step includes a stance phase and a swing phase, or an initial support step and a terminal support step. It may include.
  • the present invention can provide a gait analysis system, a method, and a computer-readable recording medium capable of generating a meaningful model for determining the severity of a knee disease through machine learning about joint angle information of a pedestrian.
  • FIG. 1 is a flow chart schematically showing the flow of a gait analysis method according to an embodiment of the present invention.
  • FIG. 2 is a flow chart schematically showing the flow of the gait analysis method according to another embodiment of the present invention.
  • FIG. 3 is a view showing an attachment position of the inertial measurement apparatus according to an embodiment of the present invention by way of example.
  • FIG. 4 is a diagram illustrating an example of a 3D simulation using a gait analysis result.
  • FIG. 5 is a diagram illustrating a clustering and severity determination process according to an embodiment of the present invention by way of example.
  • FIG. 6 is a view schematically showing the configuration of a gait analysis system according to an embodiment of the present invention.
  • FIG. 1 is a flow chart schematically showing the flow of a gait analysis method according to an embodiment of the present invention.
  • joint angle measurement step (S110), walking event extraction step (S120), walking step detection step (S130), group classification step (S140) and Severity determination step (S150) is included.
  • the lower leg joint angle of the pedestrian is measured through an inertial measurement apparatus attached to the pedestrian body.
  • the inertial measurement device may include a three-axis acceleration sensor, a three-axis gyro sensor and a geomagnetic field sensor.
  • the inertial measurement apparatus may be attached to the hip joint, the knee joint and the ankle of the pedestrian, and thus the plurality of inertial measurement apparatus may be attached to the body of the pedestrian.
  • the inertial measurement device may acquire data such as angular velocity, acceleration, and velocity at each position, and the obtained data may be used to determine the walking characteristics of the pedestrian or to determine the severity of the knee disease of the pedestrian. have.
  • the inertial measurement unit may determine the three-dimensional position of the inertial measurement unit by using data measured by the three-axis acceleration sensor, the three-axis gyro sensor, and the geomagnetic sensor.
  • the three-axis gyro sensor may measure data corresponding to rotation information and position information.
  • the walking event is extracted using a gyroscope obtained through the inertial measurement apparatus.
  • the gyroscope data may be obtained from the three-axis gyro sensor included in the inertial measurement unit.
  • the walking event may be understood as specific time information on a walking cycle, and includes time information for one step.
  • the walking event may be understood as data representing a single stride, and for example, a positive peak may represent a swing phase starting at the heel and ending at the toe.
  • the walking event may be understood to mean individual events that constitute one gait phase.
  • a gait step is detected from the gait event, and the joint angle is subdivided into the gait steps.
  • the walking step may be understood to have substantially the same meaning as the walking period described above, and includes a stance phase and a swing phase.
  • the stance phase is a period in which the foot is in contact with the ground, the initial contact (heel strike), the foot flat (foot flat, loading response), the mid stance, the heel lift (terminal) stance, heel off, and pre-swing, hoe off.
  • the swing phase is a period in which the foot is separated from the ground, and may include an accelerator, a mid swing, and a deceleration.
  • the gait step may include an initial support step and a terminal support step. More specifically, the initial support step includes an initial single support and an initial double support. Includes Terminal Single Support and Terminal Double Support.
  • the gait step detection step (S130) may be performed by classifying the gait event into a stance and an incidence or initial stage. It can be divided into support stage and terminal stage.
  • the standing and stirrups are responsible for 60% and 40% of the walking cycle, respectively, but the walking cycle sharing ratio of Initial Single Support, Initial Double Support, Terminal Single Support, and Terminal Double Support may be different.
  • the gait step detecting step S130 may detect two gait steps including different gait events, or detect four gait steps including different gait events.
  • the gait event may be detected using data obtained through the three-axis gyro sensor, and at the same time, the joint angle of each joint may be measured from the data measured by the three-axis acceleration sensor and the geomagnetic sensor. Can be. Accordingly, joint angle information corresponding to each of the walking events may be generated, and joint angle information corresponding to the walking steps detected from the walking event may be generated.
  • the group classification step S140 machine learning is performed on the joint angles broken down by the walking step to classify the group into a plurality of groups according to data characteristics.
  • the operation of classifying the plurality of groups is defined and described as clustering.
  • the walking step may be divided into two or four as described above, and may be divided into six walking steps by combining the walking steps divided into two or four.
  • the joint angle information that is the object of machine learning may be data obtained from a plurality of pedestrians, and pedestrians having similar joint angle characteristics may be clustered into the same group through the machine learning.
  • groups having similar joint angle changes for each walking stage may be classified and cluster the 100 pedestrians into a plurality of groups. .
  • the severity of the knee disease for the plurality of groups is determined.
  • joint angle information for each walking step of a normal pedestrian is required.
  • the severity of the knee disease is determined by comparing the joint angle information of the plurality of groups classified in the group classification step S140 with the joint angle information of the normal pedestrian. Therefore, it may be determined that the greater the difference with the joint angle information of the normal pedestrian, the higher the severity.
  • the severity of the knee disease may be determined by comparing the relative distances in the spaces of the joint angle information with respect to the walking angle for each step of the normal person.
  • FIG. 2 is a flow chart schematically showing the flow of the gait analysis method according to another embodiment of the present invention.
  • the gait analysis method according to another embodiment of the present invention the gait analysis method according to an embodiment of the present invention, joint angle measurement step (S210), walking event extraction step (S220), walking step A detection step S230, a group classification step S240, and a parameter screening and severity determination step S250 are included.
  • the joint angle measurement step S210 In the joint angle measurement step S210, the walking event extraction step S220, the walking step detection step S230, and the group classification step S240, the joint angle measurement step S110 and the walking event extraction described with reference to FIG. 1. Since substantially the same operations are performed as in the step S120, the walking step detection step S130, and the group classification step S140, detailed descriptions of the duplicated contents will be omitted.
  • the severity of the knee disease is determined by comparing the joint angle information.
  • the parameter selection and severity determination step (S250) may select a parameter useful for determining whether the pedestrian has a knee disease.
  • a parameter useful for determining whether the pedestrian has a knee disease By comparing the joint angle information of the normal pedestrian and the joint angle information of the plurality of groups, it is possible to determine the severity of the disease for each group, and it is a meaningful parameter that can distinguish the normal pedestrian and the knee disease group, that is, the most significant joint angle Information can be screened.
  • the joint angle information at the mid stance may be selected as a significant parameter.
  • the joint angle information at the mid stance may be selected as a significant parameter.
  • priority may be given to each parameter in response to the degree of association with the severity of the knee disease.
  • the parameter screening and severity determination step (S250) may be a plurality of selected parameters may be used to generate a model that can classify the severity of the knee disease.
  • FIG. 3 is a view showing an attachment position of the inertial measurement apparatus according to an embodiment of the present invention by way of example.
  • the inertial measurement device may be attached to the lumbar spine, hip, knee (knee) and ankle of the pedestrian.
  • a total of seven inertial measurement devices S1 to S7 may be used, and the gait event extraction step S120 described with reference to FIG. 1. Calculate the distance between the inertial measurement device (S1) and the inertial measurement device (S3), the distance between the inertial measurement device (S3) and the inertial measurement device (S5).
  • Inertial measurement devices (S1, S3, S5) are attached to the right side of the pedestrian, and in the walk event extraction step (S120) between the inertial measurement devices (S2, S4, S6) also attached to the left side of the pedestrian. Calculate the distance.
  • the inertial measurement apparatus may acquire data such as angular velocity, acceleration, and velocity at each position, and the obtained data may determine a walking characteristic of the pedestrian or the pedestrian. It can be used to determine the severity of knee disease.
  • the inertial measurement unit may determine the three-dimensional position of the inertial measurement unit by using data measured by the three-axis acceleration sensor, the three-axis gyro sensor, and the geomagnetic sensor.
  • the three-axis gyro sensor may measure data corresponding to rotation information and position information.
  • the joint angle of each joint can be calculated through the geometric analysis between the inertial measurement apparatus.
  • FIG. 4 is a diagram illustrating an example of a 3D simulation using a gait analysis result.
  • the lengths of the pedestrian's femur and the tibia may be measured in advance before gait analysis, and may be reflected in a simulation model, or the distance between the inertial measurement apparatus attached to the body of the pedestrian may be reflected.
  • the pedestrian's femur and tibia are inclined with respect to the direction perpendicular to the ground using different changes in the time between the inertial measurement devices.
  • the angle can be calculated.
  • the three-dimensional position of the inertial measurement apparatus can distinguish the stepping foot and the stepped foot, it is possible to determine the moving direction of the pedestrian.
  • a simulation model may be generated using the acceleration and the joint angle measured by the inertial measurement device and the distance between the inertial measurement device and gait analysis may be performed over time.
  • FIG. 5 is a diagram illustrating a clustering and severity determination process according to an embodiment of the present invention by way of example.
  • the joint angle information obtained through the inertial measurement device attached to the pedestrian body is subdivided into walking stages, and the plurality of pedestrians are first clustered through machine learning on the segmented joint angle information. ) To the third cluster (Cluster 3).
  • each cluster is compared by comparing the spatial distance between the normal pedestrian group and the first to third clusters.
  • the severity of the knee disease can be determined.
  • the present invention can be embodied as computer readable codes on a computer readable recording medium.
  • the computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
  • the computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.
  • functional programs, codes and code segments for implementing the present invention can be easily inferred by programmers in the art to which the present invention belongs.
  • FIG. 6 is a view schematically showing the configuration of a gait analysis system according to an embodiment of the present invention.
  • the gait analysis system 100 may include an inertial measurement apparatus 110, a gait event extractor 120, a gait step detector 130, a clustering unit 140, and a determination.
  • the unit 150 is included.
  • the inertial measurement unit 110 is attached to the pedestrian body to measure the joint angle of the lower limb of the pedestrian.
  • the inertial measurement device 110 may include a three-axis acceleration sensor, a three-axis gyro sensor, and a geomagnetic field sensor, and may be attached to the hip joint, the knee joint and the ankle of the pedestrian, and thus the inertial measurement device 110 may be attached to the pedestrian.
  • a plurality of dogs may be attached to the body.
  • the inertial measurement unit 110 may acquire data such as angular velocity, acceleration, and velocity at each position, and the obtained data may be used to determine a walking characteristic of the pedestrian or to determine the severity of the knee disease of the pedestrian. Can be.
  • the inertial measurement unit 110 may determine the three-dimensional position of the inertial measurement unit 110 by using data measured by the three-axis acceleration sensor, the three-axis gyro sensor, and the geomagnetic field sensor.
  • the three-axis gyro sensor may measure data corresponding to rotation information and position information.
  • the walking event extractor 120 extracts a walking event by using gyroscope data obtained through the inertial measurement apparatus 110.
  • the gyroscope data may be obtained from the 3-axis gyroscope sensor included in the inertial measurement unit 110.
  • the walking event may be understood as specific time information on a walking cycle, and includes time information for one step.
  • the walking event may be understood as data representing a single stride, and for example, a positive peak may represent a swing phase starting at the heel and ending at the toe.
  • the walking event may be understood to mean individual events that constitute one gait phase.
  • the walking step detection unit 130 detects a walking step from the walking event and subdivides the joint angle into the walking step.
  • the walking step may be understood to have substantially the same meaning as the walking period described above, and includes a stance phase and a swing phase.
  • the stance phase is a period in which the foot is in contact with the ground, the initial contact (heel strike), the foot flat (foot flat, loading response), the mid stance, the heel lift (terminal) stance, heel off, and pre-swing, hoe off.
  • the swing phase is a period in which the foot is separated from the ground, and may include an accelerator, a mid swing, and a deceleration.
  • the gait step may include an initial support step and a terminal support step. More specifically, the initial support step includes an initial single support and an initial double support. Includes Terminal Single Support and Terminal Double Support.
  • the gait step detection unit 130 classifies the gait event into a stance and an incline, or initially supports the gait event. It can be divided into stages and terminal support stages.
  • the standing and stirrups are responsible for 60% and 40% of the walking cycle, respectively, but the walking cycle sharing ratio of Initial Single Support, Initial Double Support, Terminal Single Support, and Terminal Double Support may be different.
  • the walking step detector 130 may detect two walking steps including different walking events, or detect four walking steps including different walking events.
  • the gait event may be detected using data obtained through the three-axis gyro sensor, and at the same time, the joint angle of each joint may be measured from the data measured by the three-axis acceleration sensor and the geomagnetic sensor. Can be. Accordingly, joint angle information corresponding to each of the walking events may be generated, and joint angle information corresponding to the walking steps detected from the walking event may be generated.
  • the walking step detection unit 130 may include a heel strike (initial contact, heel strike), foot flat (foot flat, loading response), mid stance, heel lift (terminal stance, heel off), Generate joint angle information corresponding to pre-swing (hoe off), accelerator (acceleration), mid swing (deceleration) and deceleration (deceleration).
  • the clustering unit 140 performs machine learning on the joint angles broken down by the walking step and classifies the group into a plurality of groups according to data characteristics.
  • the walking step may be divided into two or four as described above, and may be divided into six walking steps by combining the walking steps divided into two or four.
  • the joint angle information that is the object of machine learning may be data obtained from a plurality of pedestrians, and pedestrians having similar joint angle characteristics may be clustered into the same group through the machine learning.
  • groups having similar joint angle changes for each walking stage may be classified and cluster the 100 pedestrians into a plurality of groups. .
  • the determination unit 150 determines the severity of the knee disease for the plurality of groups. In order to determine the severity of the knee disease, joint angle information for each walking step of a normal pedestrian is required. The determination unit 150 determines the severity of the knee disease by comparing the joint angle information of the plurality of groups classified by the clustering unit 140 with the joint angle information of the normal pedestrian. Therefore, it may be determined that the greater the difference with the joint angle information of the normal pedestrian, the higher the severity.
  • the determination unit 150 may determine the severity by comparing the relative distances in the spaces of the joint angle information with respect to the joint angle information for each step of walking of the normal person, and select a parameter for determining the knee disease. Can be.
  • the determination unit 150 may determine the severity of the disease for each group by comparing the joint angle information of the normal pedestrian and the joint angle information of the plurality of groups, and distinguish the normal pedestrian and the knee disease group.
  • the most meaningful parameters namely the most significant joint angle information, can be selected.
  • the joint angle information at the mid stance may be selected as a significant parameter.
  • the joint angle information at the mid stance may be selected as a significant parameter.
  • priority may be given to each parameter in response to the degree of association with the severity of the knee disease.
  • the determination unit 150 there may be a plurality of parameters selected by the determination unit 150 and the selected parameters may be used to generate a model that can classify the severity of the knee disease.
  • the present invention relates to a gait analysis system, a method, and a computer-readable recording medium, and more specifically, to determine whether a pedestrian's knee disease and severity from joint angle data obtained by using an inertial measurement apparatus attached to a pedestrian body, A gait analysis system, a method for generating a model capable of determining the same, and a computer readable recording medium.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physiology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Dentistry (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Geometry (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

La présente invention concerne un système et un procédé d'analyse de marche, et un support d'enregistrement lisible par ordinateur. Selon un mode de réalisation de la présente invention, le procédé d'analyse de marche comprend les étapes consistant : à mesurer des angles d'articulation de membre inférieur d'un marcheur par l'intermédiaire d'un dispositif de mesure inertielle fixé au corps du marcheur ; à extraire un événement de marche à l'aide de données de gyroscope acquises par l'intermédiaire du dispositif de mesure inertielle ; à détecter des étapes de marche à partir de l'événement de marche, et à subdiviser les angles d'articulation pour chaque étape de marche ; à effectuer un apprentissage automatique pour les angles d'articulation subdivisés pour chaque étape de marche, de manière à classer lesdits angles en une pluralité de groupes selon des caractéristiques de données ; et à déterminer la gravité d'une maladie de l'articulation du genou pour la pluralité de groupes.
PCT/KR2017/013423 2016-11-25 2017-11-23 Système et procédé d'analyse de marche, et support d'enregistrement lisible par ordinateur WO2018097621A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2016-0158056 2016-11-25
KR1020160158056A KR20180058999A (ko) 2016-11-25 2016-11-25 보행 분석 시스템, 방법 및 컴퓨터 판독 가능한 기록매체

Publications (1)

Publication Number Publication Date
WO2018097621A1 true WO2018097621A1 (fr) 2018-05-31

Family

ID=62196035

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2017/013423 WO2018097621A1 (fr) 2016-11-25 2017-11-23 Système et procédé d'analyse de marche, et support d'enregistrement lisible par ordinateur

Country Status (2)

Country Link
KR (1) KR20180058999A (fr)
WO (1) WO2018097621A1 (fr)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102591144B1 (ko) 2018-12-27 2023-10-18 한국전자통신연구원 보행 분석 장치 및 방법
KR102399672B1 (ko) * 2019-06-11 2022-05-20 한국과학기술연구원 보행 시간-주파수 분석에 기초한 개인 식별 방법 및 시스템
KR102364184B1 (ko) * 2019-09-30 2022-02-17 한국전자기술연구원 탈부착 가능한 보행 밸런스 측정 센서
KR102318879B1 (ko) * 2019-11-25 2021-10-29 알바이오텍 주식회사 척추 측만증 및 관절 손상 예측 방법
KR102264796B1 (ko) * 2020-03-23 2021-06-11 권동혁 보행자 걸음걸이 정보를 이용한 보행자 교정 정보 제공장치
KR102545358B1 (ko) * 2021-04-09 2023-06-21 인하대학교 산학협력단 보행데이터 기반 파킨슨 증후군 중증 단계 판별 시스템 및 방법
KR102633380B1 (ko) * 2022-03-23 2024-02-06 주식회사 스파이더코어 어지럼 관련 질환 예측 방법 및 시스템

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008173250A (ja) * 2007-01-17 2008-07-31 Matsushita Electric Works Ltd 歩行動作分析装置
KR20100052373A (ko) * 2008-11-10 2010-05-19 성균관대학교산학협력단 보행 분석 방법 및 장치
JP2011177278A (ja) * 2010-02-26 2011-09-15 Tokyo Institute Of Technology 歩行障害自動分析システム
JP2012000343A (ja) * 2010-06-18 2012-01-05 Tohoku Univ 歩行解析システムおよび歩行解析方法
KR20150107342A (ko) * 2014-03-14 2015-09-23 연세대학교 원주산학협력단 근전도 및 동작을 감지하는 시스템 및 그 제어 방법

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160147475A (ko) * 2015-06-15 2016-12-23 현대자동차주식회사 캔형 열교환기

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008173250A (ja) * 2007-01-17 2008-07-31 Matsushita Electric Works Ltd 歩行動作分析装置
KR20100052373A (ko) * 2008-11-10 2010-05-19 성균관대학교산학협력단 보행 분석 방법 및 장치
JP2011177278A (ja) * 2010-02-26 2011-09-15 Tokyo Institute Of Technology 歩行障害自動分析システム
JP2012000343A (ja) * 2010-06-18 2012-01-05 Tohoku Univ 歩行解析システムおよび歩行解析方法
KR20150107342A (ko) * 2014-03-14 2015-09-23 연세대학교 원주산학협력단 근전도 및 동작을 감지하는 시스템 및 그 제어 방법

Also Published As

Publication number Publication date
KR20180058999A (ko) 2018-06-04

Similar Documents

Publication Publication Date Title
WO2018097621A1 (fr) Système et procédé d'analyse de marche, et support d'enregistrement lisible par ordinateur
WO2017051945A1 (fr) Procédé et appareil de fourniture de service d'informations médicales sur la base d'un modèle de maladie
WO2019088462A1 (fr) Système et procédé pour générer un modèle d'estimation de pression artérielle, et système et procédé d'estimation de pression artérielle
WO2018212423A1 (fr) Procédé et appareil pour calculer un niveau de sécurité
WO2018030734A1 (fr) Procédé et appareil de simulation 3d
WO2014208971A1 (fr) Méthode et appareil d'affichage d'images d'ultrasons
WO2015080431A1 (fr) Simulateur de golf et procédé de simulation de golf
WO2021075772A1 (fr) Procédé et dispositif de détection d'objet au moyen d'une détection de plusieurs zones
WO2016108327A1 (fr) Procédé de détection de véhicule, structure de base de données pour la détection de véhicule, et procédé de construction de base de données pour détection de véhicule
WO2020196985A1 (fr) Appareil et procédé de reconnaissance d'action vidéo et de détection de section d'action
WO2017095120A1 (fr) Système et procédé d'analyse de schémas de comportement utilisant une image de profondeur
JP6503079B2 (ja) 特定人物検知システム、特定人物検知方法および検知装置
WO2020032506A1 (fr) Système de détection de vision et procédé de détection de vision l'utilisant
WO2018230787A1 (fr) Dispositif et procédé d'analyse de la démarche à l'aide d'un capteur d'accélération porté à la cheville
WO2021167312A1 (fr) Procédé et dispositif de reconnaissance tactile pourvu d'un capteur lidar
JP3093346B2 (ja) 運動物体検出装置
WO2015053480A1 (fr) Système et procédé d'analyse d'échantillons biologiques
CN107007285B (zh) 基于压力与加速度传感器的跌倒检测方法
WO2023163305A1 (fr) Procédé de détection d'un type de démarche basé sur un apprentissage profond et programme informatique le mettant en oeuvre
WO2023282389A1 (fr) Procédé de calcul de masse grasse utilisant une image de tête et de cou et dispositif associé
WO2018147654A1 (fr) Procédé pour distinguer un mouvement d'animal de compagnie et appareil l'utilisant
WO2022019601A1 (fr) Extraction d'un point caractéristique d'un objet à partir d'une image ainsi que système et procédé de recherche d'image l'utilisant
WO2021241920A1 (fr) Service et système de fourniture d'instruction d'exercice dans un centre de conditionnement physique
WO2021225249A1 (fr) Système et procédé d'analyse de la démarche
WO2022010149A1 (fr) Procédé et système de génération d'ensemble de données relatives à des expressions faciales, et support d'enregistrement non transitoire lisible par ordinateur

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: 17873101

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17873101

Country of ref document: EP

Kind code of ref document: A1