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

Real-time gesture tracking method based on cascade deep neural network

A deep neural network and cascading technology, applied in the input/output process of data processing, input/output of user/computer interaction, instruments, etc., can solve problems such as difficult to use, occlusion, and slowness, and achieve high accuracy, High real-time, easy-to-reuse effects

Inactive Publication Date: 2017-09-29
苏州神罗信息科技有限公司
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In image data analysis, the traditional method is generally to distinguish hands by skin color and detect each node of the hand, but there will be serious occlusion problems, resulting in extremely unstable and slow gesture tracking, which is difficult to be practical and cannot provide real-time, stable, Precise 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
  • Real-time gesture tracking method based on cascade deep neural network
  • Real-time gesture tracking method based on cascade deep neural network
  • Real-time gesture tracking method based on cascade deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described below in conjunction with specific examples, but the protection scope of the present invention is not limited thereto.

[0026] Such as figure 1 , figure 2 , image 3 , Figure 4 with Figure 5 A real-time gesture tracking method based on a cascaded deep neural network is shown, comprising the following steps:

[0027] The first step is to obtain the original image data of the gesture through the TOF camera and the color camera, and enter the image preprocessor through the image data stream;

[0028] In the second step, the image preprocessor performs preprocessing operations on the image data. The preprocessing operations include image data reception, image data block, edge extraction using Laplacian edge extractor, and corner point extraction using Harris corner extractor. , downsampling and constructing the data packet of the downsampling data, and finally the constructed data packet is sent to the primary feature...

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 real-time gesture tracking method based on a cascade deep neural network. The method comprises: image data are obtained by a TOF camera and a color camera; an image preprocessor carries out preprocessing on the image data; essential characteristic extraction is carried out on the data after preprocessing by using a primary characteristic extractor; a cascade artificial neural network system carries out advanced characteristic abstracting processing; a mode matching device carries out mode matching according to the advanced abstract characteristics after characteristic abstract processing; and then an attitude processing center calculates all positions of twenty six nodes of a hand to obtain a hand attitude and spatial position data, and the data are transmitted to a computer application by a gesture attitude data flow. Rapid characteristic extraction, matching, and attitude calculation are carried out on image information of the human hand to guarantee the high stability, precision, and real-time performance of the calculated gesture attitude.

Description

technical field [0001] The invention relates to the fields of advanced computer vision and machine learning, in particular to a real-time gesture tracking method based on a cascaded deep neural network. Background technique [0002] With the rapid development of virtual reality, augmented reality and other industries, solving the user's motion information input has become an imminent problem, and among all human motion information, hand motion is the most intuitive and convenient. Therefore, exploring a fast, accurate and real-time gesture tracking method can solve the interaction problem of virtual reality and augmented reality at the fastest speed. [0003] At present, there are mainly data gloves and image data analysis methods for tracking gestures and postures. Among them, data gloves need to wear expensive equipment, so camera-based image data analysis has become the first choice. In image data analysis, the traditional method is generally to distinguish hands by skin...

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): G06K9/00G06K9/46G06F3/01
CPCG06F3/017G06V40/28G06V10/462
Inventor 秦静靳婷
Owner 苏州神罗信息科技有限公司
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