Unlock instant, AI-driven research and patent intelligence for your innovation.

A radar gesture recognition method based on a fusion neural network

A neural network and gesture recognition technology, applied in the field of radar gesture recognition based on fusion neural network, can solve problems such as incomplete features

Active Publication Date: 2019-05-31
CHONGQING UNIV OF POSTS & TELECOMM
View PDF7 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a radar gesture recognition method based on fusion neural network, which can effectively solve the problem of incomplete features in traditional gesture recognition, and can realize accurate classification of various gestures

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 radar gesture recognition method based on a fusion neural network
  • A radar gesture recognition method based on a fusion neural network
  • A radar gesture recognition method based on a fusion neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] Step 1. Input the transmit signal and receive signal to the mixer, filter out the high frequency part through a low-pass filter, and then obtain the intermediate frequency signal S after sampling and baseband signal processing IF (t) and IF signal frequency f IF . Specific steps are as follows:

[0072] 1.1 According to the hardware parameters of the radar, calculate the sawtooth wave signal S emitted by the FMCW radar TX (t) for

[0073]

[0074] Among them, t represents the time when the radar transmits the signal, is a linear function of the frequency of the transmitted signal as a function of time, f c is the carrier frequency, B is the bandwidth, A TX is the amplitude of the transmitted signal, and T is the signal period.

[0075] 1.2 Transmit signal delay After that, calculate the frequency shift Δφ at the receiving end as

[0076]

[0077] Among them, v is the radial motion velocity of the gesture relative to the radar, R 0 is the distance betwee...

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 radar gesture recognition method based on a fusion neural network. The method comprises the following steps of: firstly, solving a frequency spectrum of a gesture echo intermediate frequency signal by utilizing two-dimensional Fast Fourier Transform (FFT); and calculating the distance and speed parameters of the gesture target by adopting spectral peak estimation, and calculating angle parameters by utilizing a Multiplex Classification (MUSIC) method. Secondly, mapping a complete gesture action into a multi-frame distance by utilizing time accumulation of the three-dimensional parameters; And a velocity matrix diagram and an angle time diagram. Then, a fusion neural network is established by using the gesture parameter graph. And finally, performing gesture feature extraction and feature fusion by using the fusion neural network, and classifying the gesture features through a full connection layer.

Description

technical field [0001] The invention belongs to gesture recognition technology, in particular to a radar gesture recognition method based on fusion neural network. Background technique [0002] As an important part of human-computer interaction, gesture recognition affects the naturalness and flexibility of human-computer interaction and is widely used in various fields. In terms of home entertainment, the characters in the game are controlled according to the user's actions such as waving left and right in the game environment, making the user experience better. In terms of intelligent driving, since the driver may be distracted by the phone system of the car navigation system during driving, the control of the navigation system and car entertainment system can be completed by recognizing the driver's gestures to improve driving safety. [0003] In the gesture recognition of wireless technology, the gesture signal is mainly collected by wireless devices, and then the frequ...

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): G06K9/62G01S13/88
Inventor 王沙沙田增山蒋青王勇周牧
Owner CHONGQING UNIV OF POSTS & TELECOMM