Millimeter wave sensor gesture recognition method based on convolutional neural network

A technology of convolutional neural network and gesture recognition, which is applied in the field of gesture recognition based on convolutional neural network millimeter-wave sensors, can solve the problems of gesture recognition, such as limitations of lighting and climate conditions, short working distance, and low recognition accuracy, and achieve strong universal The effect of adaptability and adaptability, long-distance action, and avoidance of manual intervention

Inactive Publication Date: 2019-09-20
SOUTHEAST UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a gesture recognition method based on a convolutional neural network based on a mil...

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
  • Millimeter wave sensor gesture recognition method based on convolutional neural network
  • Millimeter wave sensor gesture recognition method based on convolutional neural network
  • Millimeter wave sensor gesture recognition method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as figure 1 , the method includes the following steps:

[0033] Step 1. Use the millimeter wave sensor to transmit frequency-modulated continuous wave signals, and perform various gestures in front of the sensor. The receiving channel of the millimeter wave sensor acquires time-domain echo signals of various types of gestures.

[0034] Step 2, performing zero-notch filtering and short-time Fourier transform on the acquired time-domain echo signal to obtain a micro-Doppler time-frequency map of finger motion;

[0035] (2.1) Carry out zero-notch filtering on the echo signal to filter out the stationary target signal. Use a notch filter to zero-filter the time-domain signal sequence x(n) of the gesture:

[0036]

[0037] Among them, y(n) is the output signal sequence; a i and b i is the filter coefficient; perform z-transformation on both sides of the formula (1), and obtain the transfer function of the digital filter as:

[0038]

[0039] Among them, z i ...

Embodiment 2

[0060] In the present invention, if image 3 As shown, a total of 12 time-frequency diagrams including coming, going, pressing down, bouncing, rotating, pushing, twisting fingers, reversing palms, sliding from left to right, sliding from right to left, zooming in, and zooming out are collected in total. Each gesture is collected 25 times, with a total of 300 time-frequency images, of which 5 time-frequency images of each type of test sample data, a total of 60 images. The original training sample data is 20 time-frequency images of each category, and the imagemagick development kit is used to sharpen each time-frequency image with a sharpening index of 10, and the image obtained after sharpening is the newly obtained training sample set; The brightness and saturation of the original training samples and the newly generated training samples after sharpening are adjusted to 80% of themselves, and a new batch of training samples is obtained; then all the above training samples ar...

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 millimeter wave sensor gesture recognition method based on a convolutional neural network, and the method comprises the steps: (1) enabling a millimeter wave sensor to emit frequency modulation continuous wave signals, carrying out the various gestures in front of the sensor, and enabling a receiving channel to obtain the time domain echo signals of the gestures; (2) obtaining a micro Doppler time-frequency diagram; (3) acquiring time-frequency diagram sample sets of different gestures; (4) preprocessing the data in the training sample set, inputting the pictures as training data into the established convolutional neural network, and carrying out supervised learning to obtain parameters of each layer of the convolutional neural network; and (5) initializing the network by using the trained parameters of each layer of the convolutional neural network to obtain an image recognition network with a gesture classification function. According to the gesture recognition method and device based on the convolutional neural network, gesture classification recognition is conducted through the convolutional neural network, manual intervention is avoided, the convolutional neural network can learn deep features of all kinds of actions, the generalization ability and adaptability are high, and the gesture recognition precision and speed are improved.

Description

technical field [0001] The invention relates to a gesture recognition method of a millimeter wave sensor, in particular to a gesture recognition method of a millimeter wave sensor based on a convolutional neural network. Background technique [0002] The interaction between human and computer has increasingly become an important part of people's daily life. With the rapid development of computer technology, the research on novel human-computer interaction technology that conforms to interpersonal communication habits has become extremely active and gratifying progress has been made. Gesture recognition research is following this trend. Gesture is a natural and intuitive mode of interpersonal communication, and gesture recognition is an indispensable key technology to realize the new generation of human-computer interaction. However, due to the diversity, ambiguity, and differences in time and space of the gesture itself, coupled with the fact that the human hand is a comple...

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
IPC IPC(8): G06F3/01G06K9/00G06K9/62G06T3/40G06T5/00
CPCG06F3/017G06T5/003G06T3/4007G06T2207/20081G06T2207/20084G06T2210/22G06V40/28G06F2218/02G06F2218/12G06F18/2414G06F18/214
Inventor 武其松徐萍张绪豪赵涤燹
Owner SOUTHEAST UNIV
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