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

Gesture recognition device, gesture recognition method and gesture recognition system

A gesture recognition and gesture technology, applied in the field of gesture recognition, can solve the problems of human-computer interaction between electronic equipment and computers, and achieve the effect of improving sensitivity and reducing production costs

Pending Publication Date: 2022-07-29
XIDIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the technical solution of gesture recognition through optical devices usually takes 10 seconds to recognize a gesture, which is difficult to meet the human-computer interaction between electronic devices and computers.

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
  • Gesture recognition device, gesture recognition method and gesture recognition system
  • Gesture recognition device, gesture recognition method and gesture recognition system
  • Gesture recognition device, gesture recognition method and gesture recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Embodiment 1: a gesture recognition method, comprising the following steps:

[0045] 1) utilize the gesture picture set to establish the database of different gestures, establish the label array of storing picture information picture array and storing label information respectively;

[0046] 2) Build a CNN model and use relu and softmax as activation functions;

[0047] 3) The computer calculates the gradient descent through the training set to fit the model; in the fitting model, a residual structure is proposed in the deep residual network, and an ultra-deep network structure is built to accelerate the training through batch normalization.

[0048] 4) Collect the motion information and angle change information of the sensors worn on the user's fingers, pass the sensors on each finger through the data selector, and perform dimensionality reduction processing, map high-dimensional data to low-dimensional space, and maintain The local structure of data in high-dimension...

Embodiment 2

[0050] Embodiment 2: a gesture recognition method, comprising the following steps:

[0051] 1) utilize the gesture picture set to establish the database of different gestures, establish the label array of storing picture information picture array and storing label information respectively;

[0052] 2) Build a CNN model and use relu and softmax as activation functions;

[0053] 3) The computer calculates the gradient descent through the training set to fit the model; in the fitting model, a residual structure is proposed in the deep residual network, and an ultra-deep network structure is built to accelerate the training through batch normalization.

[0054] 4) Collect the motion information and angle change information of the sensors worn on the user's fingers, pass the sensors on each finger through the data selector, and perform dimensionality reduction processing, map high-dimensional data to low-dimensional space, and maintain Local structure of data in high-dimensional s...

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 gesture recognition device, a gesture recognition method and a gesture recognition system.According to the gesture recognition device, a sensor with paper as a substrate is adopted, meanwhile, the substrate is made into a paper spring structure, a micro-nano structure is prepared from the paper through folding, imprinting and other technologies and used for a sensitive unit of the sensor, and the manufacturing cost of the sensor is reduced; the environmental protection grade of the sensor is improved, the sensor is easy to recycle, and meanwhile, the sensitivity of the sensor is greatly improved due to the existence of the micro-nano structure and the wrinkles; in gesture recognition, a deep residual network is adopted to solve the problem of difficulty in CNN model training, accelerated training is performed through batch standardization, finger motion information and angle change are acquired by utilizing a sensor, and meanwhile, the gesture can be judged quickly and efficiently by fusing with visual data of an RGB network camera.

Description

technical field [0001] The invention relates to the technical field of gesture recognition, in particular to a gesture recognition device, a gesture recognition method and a gesture recognition system. Background technique [0002] Gesture recognition technology can provide good human-computer interaction and improve operation convenience, and has been widely valued by the industry. At present, the lens capable of recognizing gestures can be divided into two types: a long-distance lens and a short-distance lens. The long-distance lens can be set in front of the user and face the user, such as on a TV or game console, while the short-distance lens can be set on the user. wearable device on the person. Although both distances can recognize gestures, the distance and position are different, and the gesture information that can be obtained and usage habits are of course different, resulting in different gestures for these two distances. [0003] With the development of a virtu...

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): G06F3/01G06V40/20G06K9/00G06V10/82G06V10/80G06K9/62G06N3/04G06N3/08A61B5/11
CPCG06F3/017G06F3/014G06N3/084A61B5/1116A61B5/1128G06N3/047G06N3/048G06N3/045G06F2218/08G06F18/253
Inventor 闫正杰谢涌付照棋孟天宇王浩林张鹏
Owner XIDIAN 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com