WO2019238292A1 - Procédé destiné à fournir un procédé de détermination du nombre de pas d'une personne - Google Patents

Procédé destiné à fournir un procédé de détermination du nombre de pas d'une personne Download PDF

Info

Publication number
WO2019238292A1
WO2019238292A1 PCT/EP2019/059221 EP2019059221W WO2019238292A1 WO 2019238292 A1 WO2019238292 A1 WO 2019238292A1 EP 2019059221 W EP2019059221 W EP 2019059221W WO 2019238292 A1 WO2019238292 A1 WO 2019238292A1
Authority
WO
WIPO (PCT)
Prior art keywords
steps
person
determining
sensor data
data
Prior art date
Application number
PCT/EP2019/059221
Other languages
German (de)
English (en)
Inventor
Juergen Meier
Karl Wiklund
Original Assignee
Robert Bosch Gmbh
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 Robert Bosch Gmbh filed Critical Robert Bosch Gmbh
Priority to CN201980039863.0A priority Critical patent/CN112334067A/zh
Publication of WO2019238292A1 publication Critical patent/WO2019238292A1/fr

Links

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
    • A61B5/1123—Discriminating type of movement, e.g. walking or running
    • 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
    • A61B5/1118—Determining activity level
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
    • G01C22/006—Pedometers
    • 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 invention relates to a method for providing an investigation method for a number of steps of a person.
  • the invention further relates to a device for determining a number of steps of a person.
  • a motion sensor for example an acceleration sensor or a gyroscope
  • various algorithms and methods that analyze the sensor signals have become known for evaluating the sensor data. Based on the analysis, it is then determined whether there is a step or not.
  • an acceleration sensor provides more accurate data for detecting steps when it is attached to the head compared to attaching it to an arm of a person.
  • the invention provides a method of providing an investigation method for a number of steps of a person, comprising the steps Determining sensor data using at least two sensor devices which have different types of sensors,
  • the invention provides a device for determining a number of steps of a person, comprising at least two sensor devices for determining sensor data which have different types of sensors, and a computing unit for determining a movement state of a person on the basis of evaluated Sensor data, and for selecting a method for determining a number of steps from at least two methods for step counting based on the determined movement state of the person.
  • One of the advantages achieved in this way is that the accuracy in determining the number of steps can be significantly increased, since different methods for determining steps can be appropriately selected for different situations or external conditions. In this respect, the number of undetected steps or the number of incorrectly detected steps is reduced. Another advantage is the simple and inexpensive implementation.
  • the sensor data are provided in the form of acceleration and gyroscope data.
  • the advantage of this is that sensor data are provided in a cost-effective and reliable manner, on the basis of which a movement state of the person is determined and a suitable method for determining a number of steps can thus be selected.
  • the result of the Evaluation of the sensor data provided one or more parameters.
  • a selection of a determination method for a number of steps can be selected in a simple and reliable manner.
  • the result can be displayed to a person or the like in an easily understandable form using the parameters.
  • the one or more parameters comprise at least one of the following variables: mean value, variance, rate of mean value passes, periodicity, extreme values, in particular maximum values, from the sensor data determined.
  • mean value variance
  • rate of mean value passes
  • periodicity extreme values, in particular maximum values
  • the ascertained sensor data are evaluated separately for at least two spatial directions, in particular for all three spatial directions. This further improves the reliability for the selection of the determination method for a number of steps.
  • a movement state is provided on the basis of at least two, in particular at least four different, predefinable states. This allows a movement state for a device to be specified in a sufficiently precise and at the same time efficient manner, with which a determination method for a number of steps can then be selected.
  • a first of the at least two methods for step counting comprises determining maximum values in gyroscope data and a second of the at least two methods for step counting comprises filtering acceleration data by means of an attack / release filter and comparing them with threshold values.
  • An attack / release filter is to be understood as a smoothing filter for data or a signal, which smoothes the data / signal depending on a change in the data / signal or a derived size from the data / signal.
  • the first of the sensor devices comprises at least one acceleration sensor and the second of the sensor devices comprises at least one gyroscope.
  • the computing unit is designed to calculate a number of steps of a person on the basis of the selected method and the determined sensor data. This means that not only can a suitable method for determining the number of steps be selected and made available, but also the number of steps can also be determined on the basis of the sensor data. An elaborate, separate determination of the steps is thus avoided.
  • Figure 1 shows a device according to an embodiment of the present Invention.
  • Figure 2 shows sensor data of various sensors according to one
  • Figure 3 shows steps of a method according to an embodiment of the present invention.
  • Figure 1 shows a device according to an embodiment of the present invention.
  • a device 1 is shown in detail in FIG.
  • the device 1 comprises two sensors in the form of an acceleration sensor 2 and a gyroscope 3. Both sensors 2, 3 provide corresponding measurement data to a computing unit 50.
  • the computing unit 50 comprises on the input side a filter device 4 which filters the data received from the sensors 2, 3 in each case by means of corresponding separate low-pass filters 4a, 4b.
  • the low-pass filter 4a, 4b filters high-frequency signals, which are evaluated as noise, whereas low-frequency signals can pass the filter based on steps. This improves the reliability in the detection of steps.
  • one or more parameters are determined by a parameter determination unit 5, for example an average, a variance, a periodicity or a detection of maximum values in at least some of the filtered sensor data. These parameters are then determined independently for three spatial directions, that is, along the x, y and z axes, in particular each separately for the data of the acceleration sensor 2 and the data of the gyroscope 3. In addition, it is possible to arrange further sensors and to make the data available to the arithmetic unit 50 analogously to the data of the acceleration sensor 2 and the gyroscope 3.
  • Movement state unit 6 is transmitted to the computer unit 50, which determines a current movement state of the person on the basis of the calculated characteristic variable or parameters.
  • Different movement states here four designated by reference numerals 100, 101, 102, 103, are hereby defined in advance and stored in the movement state unit 6.
  • the movement state unit 6 also provides corresponding data for the subsequent selection of a determination method for the number of steps and / or can additionally provide information for identifying incorrectly identified steps, in particular on the basis of periodicity analyzes. provide.
  • the movement state unit 6 is not only designed to determine a movement state in general, for example “running” or “running” in the narrower sense, but also generally to determine specific poses or a specific behavior of a person during running or running. This includes, for example, a movement state "listening to an audio output of a mobile phone” or “viewing a screen of a mobile phone while running", etc. This information is not only used here in particular for selecting a specific step counting method, but can also be used by other components, for example from a navigation system or for activity detection of a person or the like.
  • a tree structure can be used to decide which state of motion is present.
  • certain parameters can be used to decide which branch of the "decision tree" is followed. Decisions can be made, for example, by comparison with threshold values using binary logic.
  • State d) is always used when a person's movement cannot be classified in one of the stored states. This can reduce the number of false positive steps. Depending on the application, steps can be determined in state d) or not.
  • the determination method selection unit 8 uses various methods 20, 21 to select a corresponding method 20, 21 for determining the number of steps on the basis of the determined movement state, which then serves to determine the number of steps by means of a step counter 10.
  • Orientation information 9 and the number of steps carried out by means of the pedometer 10 are transmitted to a pedestrian coupling navigation system 11 of the navigation unit 7, with the aid of which the position of a pedestrian can be tracked.
  • steps of a person can be determined based on data from the gyrometer 3.
  • the arms of the person can swing back and forth during a normal run or race. This swing results in a clear and reliable gyrometer signal: a step can be assigned to each swing of an arm. This can be seen in the sensor data of the gyrometer on the basis of corresponding maximum values / peaks or reversal points / extreme values, on the basis of which the number of steps can then be determined.
  • FIG. 2 shows the first case, that is to say data from a run or race with arm movement, the respective sensor values of the gyroscope and the acceleration sensor being plotted over time.
  • FIG. 2 shows sensor data of various sensors according to an embodiment of the present invention.
  • FIG. 2 shows the amplitude / strength of an acceleration signal by the acceleration sensor 2 while a person is running
  • the lower half of FIG. 2 shows the amplitude / strength of a gyroscope signal for the z-axis over time during of walking is shown, the z-axis here being oriented perpendicular to the plane of an arm movement of the person.
  • the signal of the gyroscope 3 has a clear or clearer course with respect to reversal points than that of the acceleration sensor. Using an analysis of the maximum values / peaks or reversal points in the amplitude of the gyroscope signal, steps can then be counted particularly simply and reliably.
  • Figure 3 shows steps of a method according to an embodiment of the present invention.
  • FIG. 3 shows a method for providing an investigation method for a number of steps of a person.
  • sensor data are determined using at least two sensor devices 2, 3 which have different types of sensors.
  • a movement state of a person is determined by evaluating the sensor data determined.
  • a determination method is selected for a number of steps from at least two methods for step counting based on the determined state of movement of the person.

Landscapes

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

Abstract

L'invention concerne un procédé destiné à fournir un procédé de détermination du nombre de pas d'une personne, comprenant les étapes consistant à : - déterminer des données de capteur à l'aide d'au moins deux dispositifs de capteur, qui présentent différents types de capteurs, - déterminer un état de déplacement d'une personne par évaluation des données de capteur déterminées et - sélectionner un procédé de détermination du nombre de pas à partir d'au moins deux procédés destinés au comptage de pas, sur la base de l'état de déplacement déterminé de la personne.
PCT/EP2019/059221 2018-06-14 2019-04-11 Procédé destiné à fournir un procédé de détermination du nombre de pas d'une personne WO2019238292A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201980039863.0A CN112334067A (zh) 2018-06-14 2019-04-11 用于提供人员的步数的求取方法的方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102018209504.3A DE102018209504A1 (de) 2018-06-14 2018-06-14 Verfahren zum Bereitstellen eines Ermittlungsverfahrens für eine Anzahl von Schritten einer Person
DE102018209504.3 2018-06-14

Publications (1)

Publication Number Publication Date
WO2019238292A1 true WO2019238292A1 (fr) 2019-12-19

Family

ID=66240091

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2019/059221 WO2019238292A1 (fr) 2018-06-14 2019-04-11 Procédé destiné à fournir un procédé de détermination du nombre de pas d'une personne

Country Status (3)

Country Link
CN (1) CN112334067A (fr)
DE (1) DE102018209504A1 (fr)
WO (1) WO2019238292A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113324559B (zh) * 2021-05-10 2023-03-21 青岛海尔空调器有限总公司 一种运动计步方法、装置及空气处理设备

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
BHATT DEEPAK ET AL: "An intelligent framework to determine a mobile device context utilizing in-built sensors", 2015 ANNUAL IEEE INDIA CONFERENCE (INDICON), IEEE, 17 December 2015 (2015-12-17), pages 1 - 5, XP032887424, DOI: 10.1109/INDICON.2015.7443313 *
SIDDANAHALLI NINGE GOWDA ARUN KUMAR ET AL: "UMOISP: Usage Mode and Orientation Invariant Smartphone Pedometer", IEEE SENSORS JOURNAL, IEEE SERVICE CENTER, NEW YORK, NY, US, vol. 17, no. 3, 1 February 2017 (2017-02-01), pages 869 - 881, XP011639108, ISSN: 1530-437X, [retrieved on 20170109], DOI: 10.1109/JSEN.2016.2635691 *

Also Published As

Publication number Publication date
DE102018209504A1 (de) 2019-12-19
CN112334067A (zh) 2021-02-05

Similar Documents

Publication Publication Date Title
EP2569953B1 (fr) Auto-diagnose optique d'un système de caméras stéréoscopiques
DE112014002347T5 (de) Ganghaltungsmesser und Programm
DE102015103570A1 (de) Fahreranomalieerkennung
DE102009006560B4 (de) Verfahren und Sensornetz zur Merkmalsauswahl für eine Ereigniserkennung
DE102016109395A1 (de) Steuerungssystem für ein Fahrzeug
EP3017279A1 (fr) Dispositif et procédé de détermination d'un état de fermeture d'une porte ou d'une fenêtre d'une maison
EP2121417B1 (fr) Procédé et dispositif pour déterminer un décalage d'angle de braquage
DE102004032118A1 (de) Objekterkennungsverfahren für Fahrzeuge
EP3557549B1 (fr) Procédé d'évaluation d'un événement
DE112018007375T5 (de) Qualitätsüberwachungssystem
DE102006001285A1 (de) Trennung einer zufälligen Jitterkomponente und einer deterministischen Jitterkomponente
DE102009028072A1 (de) Kalibrierungsverfahren und Betriebsverfahren für einen Bewegungssensor, sowie Bewegungssensor
DE102018205561A1 (de) Vorrichtung zur Klassifizierung von Signalen
WO2019238292A1 (fr) Procédé destiné à fournir un procédé de détermination du nombre de pas d'une personne
WO2020239443A1 (fr) Procédé de surveillance de processus, programme informatique, dispositif de traitement de données, support lisible par ordinateur et dispositif de surveillance de processus
EP3391349B1 (fr) Procédé et dispositif de classement de données d'yeux ouverts d'au moins un oeil d'un passager d'un véhicule ainsi que procédé et dispositif de détection d'une envie de dormir et/ou d'un microsommeil d'un passager d'un véhicule
EP3394565B1 (fr) Méthode pour mesurer la variance dans un signal de mesure, méthode pour fusion de données, programme d'ordinateur, support de données lisible par machine et dispositif
DE102009027936A1 (de) Positionsermittlungsverfahren und Positionsermittlungsvorrichtung für ein vorausfahrendes Fahrzeug und Datenfilterungsverfahren
DE102018222584A1 (de) Verfahren zum Ermitteln von Schritten eines Lebewesens, insbesondere einer Person
DE102019201220A1 (de) Verfahren zum Ermitteln einer Anzahl von sich wiederholenden Bewegungen eines Lebewesens
WO2013083327A1 (fr) Dispositif et procédé de détection automatique d'événements dans des données de capteur
DE102020209939A1 (de) Vorrichtung und Verfahren zum Erkennen von Kopfgesten
EP0775348A1 (fr) Procede de detection de signaux par classification en logique floue
DE112020005388T5 (de) Eine Vorrichtung und ein Verfahren zum Bestimmen einer Schwimmmetrik
EP3352111B1 (fr) Procédé de détection d'événements critiques

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: 19718630

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: 19718630

Country of ref document: EP

Kind code of ref document: A1