[go: up one dir, main page]

CN110786863A - Pedestrian gait detection method based on mobile device - Google Patents

Pedestrian gait detection method based on mobile device Download PDF

Info

Publication number
CN110786863A
CN110786863A CN201911080535.3A CN201911080535A CN110786863A CN 110786863 A CN110786863 A CN 110786863A CN 201911080535 A CN201911080535 A CN 201911080535A CN 110786863 A CN110786863 A CN 110786863A
Authority
CN
China
Prior art keywords
frequency
coordinate system
under
mobile equipment
pedestrian
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN201911080535.3A
Other languages
Chinese (zh)
Other versions
CN110786863B (en
Inventor
徐强
韩业强
宋亦凡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Ten Domain Technology Co Ltd
Original Assignee
Hangzhou Ten Domain Technology Co Ltd
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 Hangzhou Ten Domain Technology Co Ltd filed Critical Hangzhou Ten Domain Technology Co Ltd
Priority to CN201911080535.3A priority Critical patent/CN110786863B/en
Publication of CN110786863A publication Critical patent/CN110786863A/en
Application granted granted Critical
Publication of CN110786863B publication Critical patent/CN110786863B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/103Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A61B5/112Gait analysis
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/68Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6887Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
    • A61B5/6898Portable consumer electronic devices, e.g. music players, telephones, tablet computers
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7253Details of waveform analysis characterised by using transforms
    • A61B5/7257Details of waveform analysis characterised by using transforms using Fourier transforms

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Physiology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Mathematical Physics (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Measurement Of Length, Angles, Or The Like Using Electric Or Magnetic Means (AREA)

Abstract

The invention discloses a pedestrian gait detection method based on mobile equipment, which comprises the following steps: a. collecting sensor data of the mobile equipment in motion under a mobile equipment coordinate system; b. calculating a rotation matrix of the mobile equipment according to the sensor data of the mobile phone, and converting the triaxial accelerometer data under the coordinate system of the mobile equipment into a geographic coordinate system; c. extracting a vertical component of the acceleration under the geographic coordinate system to obtain signal intensity; d. finding out the frequency of the first 2 bits with the maximum signal intensity in the frequency range of [0.5,4] Hz, and determining whether the ratio of the larger frequency to the smaller frequency between the two is in the range of [1.5,2.5 ]; e. the specific step detection time can be determined by using a peak detection mode. According to the method, the information of relative motion between the pedestrian and the mobile phone is filtered out according to the acceleration information frequency characteristic of walking of the pedestrian, effective data are finally extracted for gait detection, and the gait detection accuracy is improved.

Description

Pedestrian gait detection method based on mobile device
Technical Field
The invention relates to the technical field of positioning based on mobile equipment, in particular to a pedestrian gait detection method based on the mobile equipment.
Background
The current positioning technology of the mobile device needs to rely on a Pedestrian Dead Reckoning (PDR) system to a great extent, and such a scheme that a beacon node is not required to be pre-installed in a building, and the step length and the direction of a Pedestrian are calculated by using an intrinsic inertial sensor (such as an acceleration sensor, a gyroscope, a magnetometer and the like) of the mobile device, so as to estimate the track of the person who goes out in the building.
Pedestrian walking is a periodic motion process with alternating feet, and the periodicity of the periodic motion process is reflected on inertial sensor data of the mobile equipment, such as acceleration, a gyroscope and the like. A commonly used algorithm in gait detection is a wave crest/zero crossing detection algorithm based on accelerometer data, and has the advantages of simple algorithm implementation, small calculated amount and convenient real-time detection.
At present, the accuracy of hardware equipment of the inertial sensor of the mobile equipment is not high generally, the models of the sensors equipped with different equipment are different, and the collected acceleration signals contain noise due to the random change of the walking state of pedestrians, so that the accuracy of the traditional detection algorithm is not high. On the other hand, the pedestrian is in a random state in the process of using the mobile device, and may have unfixed relative motion with the device, especially in the case that the pedestrian holds the device to swing around, so that the motion information of the pedestrian is polluted by the relative change information, and the detection omission condition occurs in the gait detection.
Disclosure of Invention
The present invention is directed to a pedestrian gait detection method based on a mobile device, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a pedestrian gait detection method based on a mobile device comprises the following steps:
a. collecting sensor data of the mobile equipment in motion under a coordinate system of the mobile equipment, wherein the sensor data comprises a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer;
b. calculating a rotation matrix of the mobile equipment according to the sensor data of the mobile phone, and converting the triaxial accelerometer data under the coordinate system of the mobile equipment into a geographic coordinate system;
c. extracting a vertical component of the acceleration under the geographic coordinate system, namely a z-axis component of the geographic coordinate system, performing spectrum analysis on the vertical component by adopting fast Fourier transform, and acquiring signal intensity corresponding to each frequency with the frequency between [0 and sampling frequency/2 ];
d. finding out the frequency of the first 2 bits with the maximum signal intensity within the frequency range of [0.5,4] Hz, determining whether the ratio of the larger frequency to the smaller frequency between the two frequencies is within the range of [1.5,2.5], when the frequency is within the range of [1.5,2.5], the larger frequency is the moving frequency of the pedestrian, obtaining the signal under the corresponding frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system, and when the frequency ratio is not within the range of [1.5,2.5], the smaller frequency is the moving frequency of the pedestrian, obtaining the signal under the corresponding frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system;
e. and obtaining a time domain change curve under the corresponding frequency through inverse Fourier transform, performing peak detection on the filtered vertical component data of the accelerometer under a geographic coordinate system, and determining the specific step detection time by using a peak detection mode.
Compared with the prior art, the invention has the beneficial effects that: according to the pedestrian gait detection method based on the mobile device, the accelerometer data in the vertical direction is adopted, interference and shaking in the horizontal direction of the movement of the pedestrian can be avoided, the frequency spectrum characteristic of the accelerometer data after fast Fourier change is filtered, the noise of sensor hardware equipment is effectively filtered, and the gait detection can be effectively achieved by 95% of accuracy under the conditions that the mobile device is normally held by a hand, the body side swings, the inside of a bag, a pocket and the like.
Drawings
FIG. 1 is a schematic diagram of a moving coordinate system according to the present invention.
FIG. 2 is a schematic diagram of a geographic coordinate system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a technical scheme that:
example 1:
a pedestrian gait detection method based on a mobile device comprises the following steps:
a. collecting sensor data of the mobile equipment in motion under a coordinate system of the mobile equipment, wherein the sensor data comprises a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer;
b. calculating a rotation matrix of the mobile equipment according to the sensor data of the mobile phone, and converting the triaxial accelerometer data under the coordinate system of the mobile equipment into a geographic coordinate system;
c. extracting a vertical component of the acceleration under the geographic coordinate system, namely a z-axis component of the geographic coordinate system, performing spectrum analysis on the vertical component by adopting fast Fourier transform, and acquiring signal intensity corresponding to each frequency with the frequency between [0 and sampling frequency/2 ];
d. finding out the frequency of the first 2 bits with the maximum signal intensity within the frequency range of [0.5,4] Hz, determining whether the ratio of the larger frequency to the smaller frequency between the two frequencies is within the range of [1.5,2.5], when the frequency is within the range of [1.5,2.5], the larger frequency is the moving frequency of the pedestrian, obtaining the signal under the corresponding frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system, and when the frequency ratio is not within the range of [1.5,2.5], the smaller frequency is the moving frequency of the pedestrian, obtaining the signal under the corresponding frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system;
e. and obtaining a time domain change curve under the corresponding frequency through inverse Fourier transform, performing peak detection on the filtered vertical component data of the accelerometer under a geographic coordinate system, and determining the specific step detection time by using a peak detection mode.
Example 2:
converting accelerometer sensor data under a mobile equipment coordinate system into a horizontal component and a vertical component under a geographic coordinate system according to the rotation matrix;
and extracting a vertical component of the accelerometer under a geographic coordinate system, performing spectrum analysis on the vertical component by adopting Fast Fourier Transform (FFT), and acquiring an amplitude corresponding to each frequency between [0 and sampling frequency ]. Finding out the frequency corresponding to the maximum 2 amplitudes, and determining whether the ratio of the larger frequency to the smaller frequency between the two satisfies the relation of 2 times. If the pedestrian advancing frequency is met, reserving a larger frequency as the pedestrian advancing frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system; if the pedestrian heading frequency does not meet the requirement, reserving a smaller frequency as the pedestrian heading frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system;
and performing peak detection on the filtered vertical component data of the accelerometer in a geographic coordinate system to determine a gait detection time point.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (1)

1. A pedestrian gait detection method based on mobile equipment is characterized by comprising the following steps: the method comprises the following steps:
a. collecting sensor data of the mobile equipment in motion under a coordinate system of the mobile equipment, wherein the sensor data comprises a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer;
b. calculating a rotation matrix of the mobile equipment according to the sensor data of the mobile phone, and converting the triaxial accelerometer data under the coordinate system of the mobile equipment into a geographic coordinate system;
c. extracting a vertical component of the acceleration under the geographic coordinate system, namely a z-axis component of the geographic coordinate system, performing spectrum analysis on the vertical component by adopting fast Fourier transform, and acquiring signal intensity corresponding to each frequency with the frequency between [0 and sampling frequency/2 ];
d. finding out the frequency of the first 2 bits with the maximum signal intensity within the frequency range of [0.5,4] Hz, determining whether the ratio of the larger frequency to the smaller frequency between the two frequencies is within the range of [1.5,2.5], when the frequency is within the range of [1.5,2.5], the larger frequency is the moving frequency of the pedestrian, obtaining the signal under the corresponding frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system, and when the frequency ratio is not within the range of [1.5,2.5], the smaller frequency is the moving frequency of the pedestrian, obtaining the signal under the corresponding frequency, and performing band-pass filtering on the vertical component of the accelerometer under the geographic coordinate system;
e. and obtaining a time domain change curve under the corresponding frequency through inverse Fourier transform, performing peak detection on the filtered vertical component data of the accelerometer under a geographic coordinate system, and determining the specific step detection time by using a peak detection mode.
CN201911080535.3A 2019-11-07 2019-11-07 Pedestrian gait detection method based on mobile device Active CN110786863B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911080535.3A CN110786863B (en) 2019-11-07 2019-11-07 Pedestrian gait detection method based on mobile device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911080535.3A CN110786863B (en) 2019-11-07 2019-11-07 Pedestrian gait detection method based on mobile device

Publications (2)

Publication Number Publication Date
CN110786863A true CN110786863A (en) 2020-02-14
CN110786863B CN110786863B (en) 2022-06-14

Family

ID=69443193

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911080535.3A Active CN110786863B (en) 2019-11-07 2019-11-07 Pedestrian gait detection method based on mobile device

Country Status (1)

Country Link
CN (1) CN110786863B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428690A (en) * 2020-04-21 2020-07-17 桂林电子科技大学 Identity authentication method based on gait signal topology analysis
CN111586580A (en) * 2020-04-29 2020-08-25 杭州十域科技有限公司 Position event capturing method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090030350A1 (en) * 2006-02-02 2009-01-29 Imperial Innovations Limited Gait analysis
JP2013022188A (en) * 2011-07-20 2013-02-04 Nippon Telegr & Teleph Corp <Ntt> Gait analyzing method, gait analyzer, and program of the same
CN105180959A (en) * 2015-09-01 2015-12-23 北京理工大学 Anti-interference step counting method for wrist type step counting devices
CN106225786A (en) * 2016-08-15 2016-12-14 北京理工大学 A kind of adaptive pedestrian navigation system zero-speed section detecting method
CN107966161A (en) * 2017-11-09 2018-04-27 内蒙古大学 Walking detection method based on FFT
CN108413957A (en) * 2017-12-06 2018-08-17 上海交通大学 The method for carrying out pedestrian's course estimation under multiple carrying mode using mobile terminal

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090030350A1 (en) * 2006-02-02 2009-01-29 Imperial Innovations Limited Gait analysis
JP2013022188A (en) * 2011-07-20 2013-02-04 Nippon Telegr & Teleph Corp <Ntt> Gait analyzing method, gait analyzer, and program of the same
CN105180959A (en) * 2015-09-01 2015-12-23 北京理工大学 Anti-interference step counting method for wrist type step counting devices
CN106225786A (en) * 2016-08-15 2016-12-14 北京理工大学 A kind of adaptive pedestrian navigation system zero-speed section detecting method
CN107966161A (en) * 2017-11-09 2018-04-27 内蒙古大学 Walking detection method based on FFT
CN108413957A (en) * 2017-12-06 2018-08-17 上海交通大学 The method for carrying out pedestrian's course estimation under multiple carrying mode using mobile terminal

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428690A (en) * 2020-04-21 2020-07-17 桂林电子科技大学 Identity authentication method based on gait signal topology analysis
CN111428690B (en) * 2020-04-21 2022-08-09 桂林电子科技大学 Identity authentication method based on gait signal topology analysis
CN111586580A (en) * 2020-04-29 2020-08-25 杭州十域科技有限公司 Position event capturing method

Also Published As

Publication number Publication date
CN110786863B (en) 2022-06-14

Similar Documents

Publication Publication Date Title
US9228836B2 (en) Inference of vehicular trajectory characteristics with personal mobile devices
Negulescu et al. Comparison of seismometer and radar measurements for the modal identification of civil engineering structures
Li et al. Time-varying parameter identification of bridges subject to moving vehicles using ridge extraction based on empirical wavelet transform
CN105758404B (en) The real-time location method and system of smart machine
CN101226061A (en) Positioning method for pedestrians
CN106767888A (en) A kind of meter based on Wave crest and wave trough detection walks algorithm
CN104215238A (en) Indoor positioning method of intelligent mobile phone
CN110786863B (en) Pedestrian gait detection method based on mobile device
EP3204721A1 (en) Pedestrian dead reckoning position tracker
Ren et al. Movement pattern recognition assisted map matching for pedestrian/wheelchair navigation
CN109612463B (en) A Pedestrian Navigation and Positioning Method Based on Lateral Velocity Constraint Optimization
CN116465412A (en) An Improved PDR Indoor Localization Method Based on LSTM and Attention Mechanism
Wang et al. Improved step detection and step length estimation based on pedestrian dead reckoning
CN106052837A (en) Train vibration noise identifying method used in high-speed railway earthquake warning
US20180035382A1 (en) Method and Device for Activating and Deactivating Geopositioning Devices in Moving Vehicles
CN107749174B (en) Parking detection method, device, equipment and storage medium for anti-subway interference
US20150032033A1 (en) Apparatus and method for identifying movement in a patient
Kong et al. A real-time step detection algorithm based on dynamic peak-valley change threshold screening and dual-time threshold constraints
CN108592941A (en) A kind of step-recording method based on 3-axis acceleration
CN110887506A (en) Motion amplitude detection method and system of inertial sensor influenced by sea waves
CN107255513A (en) Skyscraper amplitude of oscillation measuring method and device
US20210370952A1 (en) Methods and systems for sequential micro-activity based driver detection on smart devices
US20230324431A1 (en) Real-time speed estimation method of moving object
CN116943130B (en) A counting method, apparatus, device and storage medium
CN114254497B (en) Method and equipment for determining motion data of sit-ups

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant