CN114034297A - Self-adaptive zero-speed interval judgment method - Google Patents

Self-adaptive zero-speed interval judgment method Download PDF

Info

Publication number
CN114034297A
CN114034297A CN202111230695.9A CN202111230695A CN114034297A CN 114034297 A CN114034297 A CN 114034297A CN 202111230695 A CN202111230695 A CN 202111230695A CN 114034297 A CN114034297 A CN 114034297A
Authority
CN
China
Prior art keywords
zero
speed
acceleration
state
foot
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.)
Pending
Application number
CN202111230695.9A
Other languages
Chinese (zh)
Inventor
苗宏胜
李海军
孙伟
蒋荣
王鹏宇
裴玉锋
徐西京
徐海刚
郑辛
纪志农
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.)
Beijing Automation Control Equipment Institute BACEI
Original Assignee
Beijing Automation Control Equipment Institute BACEI
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 Beijing Automation Control Equipment Institute BACEI filed Critical Beijing Automation Control Equipment Institute BACEI
Priority to CN202111230695.9A priority Critical patent/CN114034297A/en
Publication of CN114034297A publication Critical patent/CN114034297A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a self-adaptive zero-speed interval judgment method, which comprises the steps of fixing a micro-inertia measurement unit on the foot of a pedestrian, collecting the acceleration and the angular rate of the foot of a plurality of groups of pedestrians in different motion states, carrying out noise reduction treatment on the acceleration and the angular rate, and then carrying out statistics on the peak values of the acceleration in gait cycles at each zero-speed moment and non-zero-speed moment so as to extract the motion state characterization quantity; constructing a training sample set based on the motion state characteristic quantity, the acceleration and the angular rate in each zero-speed moment and non-zero-speed moment gait cycle; classifying the zero-velocity points and the non-zero-velocity points by adopting a support vector machine algorithm, and solving boundary conditions and constructing a decision function; and adaptively adjusting the zero-speed detection criterion of the next period according to the peak value of the acceleration output by the micro-inertia measurement unit in the current gait period, and judging whether the current zero-speed state is the zero-speed state, thereby realizing the judgment of the zero-speed interval. The invention improves the accuracy of zero-speed detection and further improves the autonomous navigation precision of pedestrians.

Description

Self-adaptive zero-speed interval judgment method
Technical Field
The invention belongs to the field of pedestrian micro autonomous navigation, and relates to a self-adaptive zero-speed interval judgment method.
Background
When the traditional pedestrian navigation technology based on zero speed correction is used for zero speed detection, a fixed threshold value zero speed detection criterion is usually adopted, when the output angular rate of the micro-inertia measurement unit, the amplitude value and the standard deviation of acceleration are smaller than a certain fixed threshold value, the current state is judged to be in a zero speed state, and when a pedestrian performs high-dynamic motion (such as running and jumping), misjudgment and missed judgment are easily caused.
Disclosure of Invention
The invention aims to provide a zero-speed detection method with high accuracy and strong adaptability, so as to solve the problems that the traditional fixed threshold zero-speed detection algorithm is easy to cause misjudgment and missed judgment in a complex motion state and improve the precision of a pedestrian micro autonomous navigation system.
In order to solve the technical problem, the invention provides a self-adaptive zero-speed interval judgment method, which adopts the following technical scheme:
fixing a micro-inertia measurement unit on the foot of a pedestrian, collecting the acceleration and angular rate of the foot of a plurality of groups of pedestrians in different motion states, carrying out noise reduction processing on the acceleration and angular rate, and then carrying out statistics on the peak values of the acceleration in gait cycles at each zero-speed moment and non-zero-speed moment so as to extract the motion state characterization quantity;
constructing a training sample set based on the motion state characteristic quantity, the acceleration and the angular rate in each zero-speed moment and non-zero-speed moment gait cycle;
classifying the zero-velocity points and the non-zero-velocity points by adopting a support vector machine algorithm, and solving boundary conditions to obtain decision functions of the zero-velocity points and the non-zero-velocity points;
and adaptively adjusting the zero-speed detection threshold of the next period according to the peak value of the acceleration output by the micro-inertia measurement unit in the current gait period, and judging whether the current zero-speed state is the zero-speed state, thereby realizing the judgment of the zero-speed interval.
The method has the beneficial effects that the method adopts a support vector machine algorithm to classify the foot angular velocity and the acceleration of the pedestrian in the zero-velocity state and the non-zero-velocity state, adaptively adjusts the zero-velocity detection criterion, improves the zero-velocity detection accuracy and the adaptability to complex gait, and further improves the autonomous navigation precision of the pedestrian.
Drawings
Fig. 1 is a block diagram illustrating a basic principle of an adaptive zero-speed interval determination method according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in 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. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. 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.
As shown in fig. 1, the adaptive zero-speed interval determination method provided by the present invention is as follows:
fixing a micro-inertia measurement unit on the foot of a pedestrian, collecting the acceleration and angular rate of the foot of a plurality of groups of pedestrians in different motion states (including walking, running, jumping and the like), carrying out noise reduction treatment on the acceleration and angular rate, and then carrying out statistics on the peak values of the acceleration in gait cycles at each zero-speed moment and non-zero-speed moment to extract the motion state characterization quantity;
constructing a training sample set based on the motion state characteristic quantity, the acceleration and the angular rate in each zero-speed moment and non-zero-speed moment gait cycle;
classifying the zero-velocity point and the non-zero-velocity point by adopting a support vector machine algorithm, and solving a boundary condition, namely a functional relation between a zero-velocity detection threshold value and acceleration and angular rate peak values;
and the threshold value of the zero-speed detection of the next period is adaptively adjusted according to the peak value of the acceleration output by the micro-inertia measurement unit in the current gait period, and whether the current zero-speed state is the zero-speed state is judged, so that the judgment of a zero-speed interval is realized, the probability of erroneous judgment and missed judgment is reduced, and the accuracy and the adaptability of the zero-speed detection are improved.
In some embodiments of the present invention, the motion state characteristic amount extraction method includes:
(1) raw inertial data acquisition
The micro-inertia measurement unit is fixed on the foot of the pedestrian, and a plurality of groups of raw data of the angular velocity and the acceleration of the foot of the pedestrian under different motion states (including walking, running, jumping and the like) are collected.
(2) Motion state characterization quantity extraction
Calculating the vertical acceleration of the noise-reduced foot after deducting the gravity acceleration at the time t as follows:
At＝at-g
wherein a istThe vertical acceleration is acquired at the moment t, and g is the local gravity acceleration. Setting a certain window, and finding A in the windowtPeak value of (a):
Figure BDA0003315809070000031
wherein T isvIs the window width. Since the foot needs to move faster as the moving speed increases during walking, the peak value of the acceleration of the foot increases in the non-zero speed interval of the gait cycle. Thus can be used
Figure BDA0003315809070000032
The state of motion is characterized in that,
Figure BDA0003315809070000033
the larger the movement speed is.
In some embodiments of the present invention, the training sample set constructing method is as follows:
classifying and marking the collected foot angular rate and acceleration of the pedestrian under different motion states according to whether the foot angular rate and the acceleration are in a zero-speed state, and constructing a training sample set as follows:
Figure BDA0003315809070000041
Figure BDA0003315809070000042
Figure BDA0003315809070000043
Figure BDA0003315809070000044
wherein, ω istIs a model of the angular velocity of the foot of a pedestrian,
Figure BDA0003315809070000045
respectively is the standard deviation of the acceleration and the angular rate, and N is the sample capacity of the training set; z is a radical ofn0 or 1, zn0 denotes a non-zero velocity state, zn1 represents the zero speed state.
Further, a support vector machine algorithm is adopted for TA、Tω、
Figure BDA0003315809070000046
Classifying to obtain the boundary between zero-speed state and non-zero-speed state under different motion states, and determining the boundarySolving the expression, wherein the expression of the boundary condition is as follows:
Figure BDA0003315809070000047
Figure BDA0003315809070000048
Figure BDA0003315809070000049
Figure BDA00033158090700000410
wherein, phi ([ A ]p A]T)、Φ(Ap ω]T)、Φ(Ap σA]T)、Φ(Ap σω]T) Are respectively [ A ]p A]T、[Ap ω]T、[Ap σA]T、[Ap σω]TMapping to a high dimension.
Further, a decision function is constructed according to the boundary conditions
Figure BDA00033158090700000411
Figure BDA0003315809070000051
Figure BDA0003315809070000052
Figure BDA0003315809070000053
If A of the foot of the pedestrian at a certain momentt、ωt、
Figure BDA0003315809070000054
At the same time satisfy
Figure BDA0003315809070000055
The current state is considered as the zero speed state, otherwise, the state is the non-zero speed state.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (5)

1. A self-adaptive zero-speed interval determination method is characterized in that,
fixing a micro-inertia measurement unit on the foot of a pedestrian, collecting the acceleration and angular rate of the foot of a plurality of groups of pedestrians in different motion states, carrying out noise reduction processing on the acceleration and angular rate, and then carrying out statistics on the peak values of the acceleration in gait cycles at each zero-speed moment and non-zero-speed moment so as to extract the motion state characterization quantity;
constructing a training sample set based on the motion state characteristic quantity, the acceleration and the angular rate in each zero-speed moment and non-zero-speed moment gait cycle;
classifying the zero-velocity points and the non-zero-velocity points by adopting a support vector machine algorithm, and solving boundary conditions to obtain decision functions of the zero-velocity points and the non-zero-velocity points;
and adaptively adjusting the zero-speed detection threshold of the next period according to the peak value of the acceleration output by the micro-inertia measurement unit in the current gait period, and judging whether the current zero-speed state is the zero-speed state, thereby realizing the judgment of the zero-speed interval.
2. The adaptive zero-velocity interval decision method according to claim 1, wherein the motion state characteristic quantity extraction method is:
calculating the vertical acceleration A after the noise reduction by deducting the gravity acceleration at the time tt(ii) a Setting a certain window, and finding A in the windowtPeak value of
Figure FDA0003315809060000011
Namely the motion state characterization quantity.
3. The adaptive zero-velocity interval decision method according to claim 1 or 2, wherein the training sample set construction method is as follows:
classifying and marking the collected foot angular rate and acceleration of the pedestrian under different motion states according to whether the foot angular rate and the acceleration are in a zero-speed state, and constructing a training sample set as follows:
Figure FDA0003315809060000012
Figure FDA0003315809060000013
Figure FDA0003315809060000014
Figure FDA0003315809060000015
wherein, ω istIs a model of the angular velocity of the foot of a pedestrian,
Figure FDA0003315809060000021
respectively is the standard deviation of the acceleration and the angular rate, and N is the sample capacity of the training set; z is a radical ofnEither 0 or 1, represents a non-zero speed state and a zero speed state.
4. According toThe adaptive zero-speed interval decision method of claim 3, characterized by using a support vector machine algorithm for TA、Tω、
Figure FDA0003315809060000022
And classifying to obtain the boundary between the zero-speed state and the non-zero-speed state under different motion states, wherein the boundary condition expression form is as follows:
Figure FDA0003315809060000023
Figure FDA0003315809060000024
Figure FDA0003315809060000025
Figure FDA0003315809060000026
wherein, phi ([ A ]p A]T)、Φ([Ap ω]T)、Φ([Ap σA]T)、Φ([Ap σω]T) Are respectively [ A ]p A]T、[Ap ω]T、[Ap σA]T、[Ap σω]TMapping to a high dimension.
5. The adaptive zero-speed interval decision method according to claim 4, wherein a decision function is constructed based on boundary conditions plus:
Figure FDA0003315809060000027
Figure FDA0003315809060000028
Figure FDA0003315809060000029
Figure FDA00033158090600000210
if A of the foot of the pedestrian at a certain momentt、ωt、
Figure FDA0003315809060000031
At the same time satisfy
Figure FDA0003315809060000032
The current state is considered as the zero speed state, otherwise, the state is the non-zero speed state.
CN202111230695.9A 2021-10-22 2021-10-22 Self-adaptive zero-speed interval judgment method Pending CN114034297A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111230695.9A CN114034297A (en) 2021-10-22 2021-10-22 Self-adaptive zero-speed interval judgment method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111230695.9A CN114034297A (en) 2021-10-22 2021-10-22 Self-adaptive zero-speed interval judgment method

Publications (1)

Publication Number Publication Date
CN114034297A true CN114034297A (en) 2022-02-11

Family

ID=80135156

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111230695.9A Pending CN114034297A (en) 2021-10-22 2021-10-22 Self-adaptive zero-speed interval judgment method

Country Status (1)

Country Link
CN (1) CN114034297A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116576851A (en) * 2022-12-26 2023-08-11 中国人民解放军陆军装甲兵学院 Pedestrian foot zero speed judging method based on support vector machine algorithm

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103630147A (en) * 2013-11-26 2014-03-12 哈尔滨工程大学 Zero-speed detection method for individually autonomous navigation system based on hidden Markov model (HMM)
CN104296750A (en) * 2014-06-27 2015-01-21 大连理工大学 Zero speed detecting method, zero speed detecting device, and pedestrian navigation method as well as pedestrian navigation system
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
CN106767794A (en) * 2017-01-19 2017-05-31 南京航空航天大学 A kind of elastic zero-speed method of discrimination based on pedestrian movement's modal identification
CN108362282A (en) * 2018-01-29 2018-08-03 哈尔滨工程大学 A kind of inertia pedestrian's localization method based on the adjustment of adaptive zero-speed section
CN109883429A (en) * 2019-04-15 2019-06-14 山东建筑大学 Zero-speed detection method and indoor pedestrian's inertial navigation system based on Hidden Markov Model
CN110455316A (en) * 2019-08-27 2019-11-15 哈尔滨工业大学 A kind of adaptive zero-speed section detecting method
CN110553643A (en) * 2019-09-17 2019-12-10 电子科技大学 pedestrian self-adaptive zero-speed updating point selection method based on neural network

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103630147A (en) * 2013-11-26 2014-03-12 哈尔滨工程大学 Zero-speed detection method for individually autonomous navigation system based on hidden Markov model (HMM)
CN104296750A (en) * 2014-06-27 2015-01-21 大连理工大学 Zero speed detecting method, zero speed detecting device, and pedestrian navigation method as well as pedestrian navigation system
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
CN106767794A (en) * 2017-01-19 2017-05-31 南京航空航天大学 A kind of elastic zero-speed method of discrimination based on pedestrian movement's modal identification
CN108362282A (en) * 2018-01-29 2018-08-03 哈尔滨工程大学 A kind of inertia pedestrian's localization method based on the adjustment of adaptive zero-speed section
CN109883429A (en) * 2019-04-15 2019-06-14 山东建筑大学 Zero-speed detection method and indoor pedestrian's inertial navigation system based on Hidden Markov Model
CN110455316A (en) * 2019-08-27 2019-11-15 哈尔滨工业大学 A kind of adaptive zero-speed section detecting method
CN110553643A (en) * 2019-09-17 2019-12-10 电子科技大学 pedestrian self-adaptive zero-speed updating point selection method based on neural network
US20210080261A1 (en) * 2019-09-17 2021-03-18 University Of Electronic Science And Technology Of China Pedestrian adaptive zero-velocity update point selection method based on a neural network

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
孙伟;丁伟;闫慧芳;: "K均值聚类自适应零速检测人员定位技术", 传感技术学报, no. 02 *
田晓春;陈家斌;韩勇强;杨黎明;尹静源;: "多条件约束的行人导航零速区间检测算法", 中国惯性技术学报, no. 01 *
纪志农等: "基于 SVM 自适应零速检测的行人自主导航算法", 《中国惯性技术学报》, vol. 29, no. 5, pages 604 - 616 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116576851A (en) * 2022-12-26 2023-08-11 中国人民解放军陆军装甲兵学院 Pedestrian foot zero speed judging method based on support vector machine algorithm

Similar Documents

Publication Publication Date Title
Paul et al. An effective approach for human activity recognition on smartphone
CN103712632B (en) A kind of step-recording method based on 3 axle accelerometers and pedometer
JP6567658B2 (en) Device and method for classifying user activity and / or counting user steps
CN107343789B (en) Step motion identification method based on three-axis acceleration sensor
CN107133970B (en) Online multi-target tracking method and device based on motion information
CN106204586B (en) A kind of moving target detecting method under complex scene based on tracking
CN103616034A (en) Network pedometer based on Bluetooth and step calculation method
CN109540133B (en) Self-adaptive gait division method and system based on micro-inertia technology
CN111288986B (en) Motion recognition method and motion recognition device
US10078373B2 (en) Method of temporal segmentation of an instrumented gesture, associated device and terminal
CN114034297A (en) Self-adaptive zero-speed interval judgment method
CN109977885A (en) A kind of people's vehicle automatic identifying method and device based on Doppler Feature
CN111161325A (en) Three-dimensional multi-target tracking method based on Kalman filtering and LSTM
CN107289966A (en) Method and apparatus for counting step number
CN111536989A (en) Adaptive time window step counting method based on peak detection
CN111603169A (en) Pedestrian gait recognition method based on MEMS inertial sensor
CN108898062B (en) Hand motion recognition method based on improved signal segment extraction algorithm
CN107392106B (en) Human activity endpoint detection method based on double thresholds
CN107688828B (en) Bus crowding degree estimation method based on mobile phone sensor
CN114061616A (en) Self-adaptive peak detection step counting method
CN103826202B (en) Based on the method that mobile phone sensor information improves the bounce of WiFi positioning results
CN116793364A (en) Indoor positioning system and method based on dead reckoning
CN107886524B (en) Method for identifying motion track of elevator door
CN107800863B (en) Control method for real-time scene detection by wireless communication device
KR101713496B1 (en) System and method for zero-delay real time step detection utilizing an accelerometer sensor

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20220211