A pedestrian gait detection method based on mobile devices

A mobile device, gait detection technology, applied in the directions of diagnostic recording/measurement, medical science, diagnosis, etc., can solve the problems of missed detection of gait detection, low accuracy, noise in the acceleration signal, etc., to avoid disturbing shaking, filtering effect of noise

Active Publication Date: 2022-06-14
杭州十域科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, due to the generally low precision of the hardware equipment of the inertial sensor of the mobile device, different types of sensors equipped with different devices, and random changes in the walking state of pedestrians, the collected acceleration signal contains noise, which makes the accuracy of the traditional detection algorithm not high.
On the other hand, pedestrians are in a random state when using a mobile device, and may have unfixed relative motion with the device, especially when the pedestrian is holding the device and swinging around, resulting in relatively changing information polluting the pedestrian's motion information , the gait detection has missed detection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A pedestrian gait detection method based on mobile devices
  • A pedestrian gait detection method based on mobile devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] A pedestrian gait detection method based on a mobile device, the method comprising the following steps:

[0019] a. Collect the sensor data of the mobile device in motion in the mobile device coordinate system, including the three-axis accelerometer, the three-axis gyroscope, and the three-axis magnetometer;

[0020] b. Calculate the rotation matrix of the mobile device according to the sensor data of the mobile device, and convert the three-axis accelerometer data in the mobile device coordinate system to the geographic coordinate system;

[0021] c. Extract the vertical component of the acceleration in the geographic coordinate system, that is, the z-axis component of the geographic coordinate system, and perform spectrum analysis on it using fast Fourier transform to obtain the corresponding frequency of each frequency between [0, sampling frequency / 2] signal strength;

[0022] d. Find the frequencies of the top 2 digits with the highest signal strength within the f...

Embodiment 2

[0025] Convert the accelerometer sensor data in the mobile device coordinate system into the horizontal and vertical components in the geographic coordinate system according to the rotation matrix;

[0026] The vertical component of the accelerometer in the geographic coordinate system is extracted, and the fast Fourier transform (FFT) is used for spectrum analysis to obtain the amplitude corresponding to each frequency between [0, sampling frequency]. Find the frequencies corresponding to the maximum two amplitudes, and confirm whether the ratio of the larger frequency to the smaller frequency between the two satisfies the ~2 times relationship. If it is satisfied, keep the larger frequency as the pedestrian advancing frequency, and perform bandpass filtering on the vertical component of the accelerometer in the geographic coordinate system; The vertical component of is band-pass filtered;

[0027] For the vertical component data of the filtered accelerometer in the geograph...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a pedestrian gait detection method based on a mobile device. The method comprises the following steps: a. collecting sensor data of the mobile device in motion under the coordinate system of the mobile device; b. calculating according to the sensor data of the mobile phone Get the rotation matrix of the mobile device, convert the three-axis accelerometer data in the mobile device coordinate system to the geographic coordinate system; c, extract the vertical component of the acceleration in the geographic coordinate system, and obtain the signal strength; d, find out the frequency in [ 0.5, 4] Hz frequency range of the first two frequencies with the largest signal strength, confirm whether the ratio between the larger frequency and the smaller frequency is within the range of [1.5, 2.5]; e, using the peak detection method that is A specific step detection time can be determined. According to the frequency characteristics of the acceleration information of pedestrians walking, the method filters out the relative motion information of pedestrians and mobile phones, and finally extracts effective data for gait detection, improving the accuracy of gait detection.

Description

technical field [0001] The invention relates to the technical field of positioning based on mobile devices, in particular to a pedestrian gait detection method based on mobile devices. Background technique [0002] The current positioning technology of mobile devices relies heavily on the pedestrian dead reckoning (Pedestrian Dead Reckoning, PDR) system, which does not require pre-installed beacon nodes in buildings and uses inherent inertial sensors (such as A scheme to calculate the step length and direction of pedestrians, and to infer the traces of pedestrians in buildings. [0003] Pedestrian walking is a periodic motion process of alternating feet, and its periodicity will be reflected in the inertial sensor data of mobile devices, such as acceleration, gyroscope, etc. A commonly used algorithm in gait detection is the peak / zero-crossing detection algorithm based on accelerometer data. [0004] At present, due to the generally low accuracy of the hardware devices of ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/11A61B5/00
CPCA61B5/112A61B5/6898A61B5/7257A61B5/7235
Inventor 徐强韩业强宋亦凡
Owner 杭州十域科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap