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

Gesture interaction method and system

An interaction method and gesture technology, applied in the field of image processing, can solve problems such as unsatisfactory real-time performance, achieve real-time gesture interaction, reduce computing time, and reduce complexity

Inactive Publication Date: 2017-07-14
深圳市石代科技集团有限公司
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the object of the present invention is to provide a gesture interaction method and system to solve the technical problem of unsatisfactory real-time performance in the timing interaction method of the prior art

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 interaction method and system
  • Gesture interaction method and system
  • Gesture interaction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 As shown, the embodiment of the present invention provides a gesture interaction method, and the specific steps are as follows:

[0065] S100. Real-time collection of 3D images of gestures

[0066] Collect dynamic 3D images of gestures in real time through the camera.

[0067] S101. Preprocess the 3D image to obtain the preprocessed 3D image

[0068] Perform preprocessing on the collected three-dimensional images. The preprocessing method in this embodiment is preferably one or more of fast Fourier transform, local adaptive threshold algorithm and morphology, and the morphology preprocessing method is preferably Expansion and corrosion. The fast Fourier transform is used to eliminate the noise, the local adaptive threshold algorithm is used for binarization to eliminate the influence of illumination, and the interesting part of the image is highlighted through morphological operations such as expansion and corrosion.

[0069] S102. Perform edge extraction and b...

Embodiment 2

[0094] Such as image 3 As shown, this embodiment provides an interactive device, including an image acquisition module 100, a preprocessing module 101, an image segmentation module 102, a correction module 103, a deep convolutional neural network module 104, an interactive state machine module 105, and a judgment module 106. The image acquisition module 100 is used for real-time acquisition of three-dimensional images of gestures; the preprocessing module 101 is used for preprocessing the three-dimensional images to obtain preprocessed three-dimensional images; the image segmentation module 102 is used for performing preprocessing on the preprocessed three-dimensional images Edge extraction and binarization to generate an edge matrix and a binary matrix; the correction module 103 is used to fill the target enclosed area on the edge matrix, and calculate the edge matrix and the binary matrix after the target enclosed area is filled to generate a correction two Value matrix; the ...

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 provides a gesture interaction method and system and relates to the technical field of image processing. The gesture interaction method comprises the steps that a three-dimensional image of a gesture is collected in real time; the three-dimensional image is preprocessed to obtain a preprocessed three-dimensional image; the preprocessed three-dimensional image is subjected to edge extraction and binarization to generate an edge matrix and a binary matrix; the edge matrix is subjected to target closed region filling, and the edge matrix obtained after target closed region filling and the binary matrix are subjected to and calculation to generate a corrected binary matrix; the corrected binary matrix is processed through a deep convolutional neural network to output an interaction vector; an interaction class state machine performs state updating according to the output interaction vector; whether the updated state has a set change is judged; if not, an interaction is directly ended; and if yes, an interaction action is triggered, and then the interaction is ended. The problem that the real-time performance of all gesture interaction methods in the prior art is not ideal is solved, and the technical effect of improving the real-time performance of a gesture interaction is achieved.

Description

Technical field [0001] The invention relates to the technical field of image processing, in particular to a gesture interaction method and system. Background technique [0002] Some existing game devices (such as xbox, Kinect, etc.) have implemented gesture interactive operations. The existing real-time gesture interaction simulates simple interaction operations based on pattern recognition or motion detection. [0003] There are currently three popular gesture recognition algorithms: [0004] (1) Gesture recognition based on pattern matching. The regional feature of the gesture is used as the feature to be recognized, and the preset environment parameters are used to perform affine transformation on the target and then match the preset template. This method has strong stability, but the recognition is not flexible enough, the fault tolerance is very low, the real-time performance is low, and it is powerless when encountering a variable target. [0005] (2) Gesture recognition base...

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): G06F3/01G06K9/00G06K9/46G06N3/04
CPCG06F3/017G06N3/04G06V20/64G06V40/28G06V10/44
Inventor 肖志勇
Owner 深圳市石代科技集团有限公司
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com