Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A gait recognition method with independent directions based on commercial Wi-Fi

A commercial technology for gait recognition, which is applied in the field of computer networks, can solve the problem of single gait recognition method, and achieve the effect of low price, good versatility, and cost saving

Active Publication Date: 2019-05-03
TIANJIN UNIV
View PDF10 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a direction-independent gait recognition method based on commercial Wi-Fi. The present invention is mainly used to solve the problem of walking along a single path in the existing gait recognition method. The information above is mapped to the direction of the subject's movement, getting rid of the dependence of the path, obtaining the direction-independent gait information, and realizing the gait recognition of moving in any straight direction. See the description below for details:

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 gait recognition method with independent directions based on commercial Wi-Fi
  • A gait recognition method with independent directions based on commercial Wi-Fi
  • A gait recognition method with independent directions based on commercial Wi-Fi

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A direction-independent gait recognition method based on commercial Wi-Fi, see figure 1 , the method includes the following steps:

[0047] 101: The subject repeatedly walks a specified distance in a predetermined area, and collects the subject's CSI signal through a commercial Wi-Fi device;

[0048] 102: Use the Butterworth bandpass filter to denoise all the amplitude data, and use the PCA dimensionality reduction algorithm to remove data redundancy and further reduce noise;

[0049] 103: Use the data after PCA dimensionality reduction to perform motion detection according to the different states of the PSD distribution of the CSI signal in the walking and stationary states;

[0050] 104: According to the Fresnel theory, the number of Fresnel zones passing through and the phase delay of the amplitude signal are measured from the CSI signal, and the walking direction of the subject is deduced based on these data;

[0051] 105: Perform STFT (short-time Fourier transfor...

Embodiment 2

[0058] Below in conjunction with concrete example, calculation formula, the scheme in embodiment 1 is further introduced, see the following description for details:

[0059] 1. Using commercial Wi-Fi to collect CSI signals

[0060] Since the embodiment of the present invention is designed for a smaller application environment, the number of people that can be recognized is limited, here we take the number of 6 people that can make the recognition accuracy within an acceptable range.

[0061] 1) One commercial Wi-Fi device acts as the transmitting end, and the other two commercial Wi-Fi devices act as the receiving end, forming two pairs of links. These two pairs of links are placed vertically to form a Cartesian coordinate system. The transmitter is located at the origin of the coordinates, and the two receivers are located on the X-axis and Y-axis respectively, 7m away from the receiver;

[0062] For example: a router, as a transmitter, continuously transmits wireless signal...

Embodiment 3

[0142] The functions and effects of the above-mentioned embodiments 1 and 2 are shown below in conjunction with the accompanying drawings.

[0143] This example uses CSI data processing as an example to give a specific implementation method, and the specific steps are as follows:

[0144] Use one laptop as the Wi-Fi access point, that is, the sender, and the other two laptops as the receiver, all three laptops are installed with Intel 5300NIC and Ubuntu 14.04LTS desktop system, and the transmitter has 3 antennas, each There are 3 antennas at the receiving end, the distance between the 3 antennas at each end is one wavelength (5.79cm), and they are located on a straight line. The transmitting end and the receiving end are placed on three small table boards, 40cm away from the ground. At the same time, the transmitting end and each receiving end form a pair of links. The two pairs of links are perpendicular to each other to form a plane rectangular coordinate system. The transmi...

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 Wi-Fi (Wireless Fidelity) based on commercial use. According to the gait recognition method with the independent direction of the Wi-Fi, a subject repeatedly walks for a specified distance in a preset area and passes through commercial Wi-Fi; the Wi-Fi device collects a CSI signal of the subject; motion detection is carried out according to different states of CSI signalPSD distribution in walking and static states by using PCA dimension-reduced data, and the walking direction of the subject is derived; STFT is carried out on the first ten principal component data after dimension reduction, a time domain signal is converted to a time-frequency domain, 10 spectrograms with the horizontal axis as time and the longitudinal axis as frequency are obtained, and the spectrograms are denoised through a two-dimensional Gaussian low-pass filter; according to the derived direction, mapping the spectrogram to the direction reflecting the real movement of the human body,and carrying out error correction and fusion to obtain a spectrogram; extracting manual features from the spectrogram, and obtaining automatic features from a Gabor filter; and inputting the two features into a support vector machine with a radial basis function to realize gait recognition.

Description

technical field [0001] The invention relates to a computer network, in particular to the field of feature extraction and data mining, in particular to a direction-independent gait recognition method based on commercial Wi-Fi. Background technique [0002] As a popular biometric technology for human identification, gait recognition uses the way of walking to identify individuals. Gait has prominent advantages over other forms of biometrics, such as faces, fingerprints, and irises, in the following ways: (1) Unique: Everyone seems to have a unique way of walking, providing unique cues for identification. (2) Unobtrusive: it requires no user intervention. Due to its wide-ranging needs in different fields, this technology has attracted extensive attention in security monitoring, healthcare, and human-computer interaction. There are various sensing technologies for gait recognition, ranging from wearable sensor-based, computer vision-based to environment perception-based method...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62H04B17/30
CPCY02D30/70
Inventor 王聪张蕾王志锐
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products