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

A polymorphic gesture recognition method based on dynamic and static fusion

A gesture recognition and dynamic gesture technology, applied in the field of interactive teaching, can solve the problem that the recognition rate of multi-type gestures is difficult to meet the intelligent gestures, etc., and achieve the effect of improving the recognition rate, robustness and good service.

Active Publication Date: 2018-12-25
UNIV OF JINAN
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the currently commonly used gesture recognition methods require manual design of feature extraction and classifiers, the robustness and generalization of the recognition results, and the recognition rate for multiple types of gestures are difficult to meet the requirements of the intelligent gesture teaching interface.

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 polymorphic gesture recognition method based on dynamic and static fusion
  • A polymorphic gesture recognition method based on dynamic and static fusion
  • A polymorphic gesture recognition method based on dynamic and static fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be described in further detail below in conjunction with the accompanying drawings:

[0050] Caffe (Convolutiona Architecture for Fast Feature Embedding) is currently the most widely used deep learning platform in the image field. Based on the VS2013 platform, the present invention combines the Caffe platform with a gesture recognition model of deep learning to create an interactive teaching interface. The present invention studies the recognition algorithm for gestures in the interactive teaching interface, and combines the gesture recognition algorithm of deep learning to propose a dynamic and static fusion polymorphic gesture recognition algorithm. Based on the big data of two thousand people, the gesture library is Static gesture pictures and dynamic gesture sequences are processed to generate a dynamic and static fusion gesture data set, and then input into the deep learning network for training. Through repeated training, it is found that t...

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 dynamic and static fusion polymorphic gesture recognition method, belonging to the interactive teaching field. The dynamic and static fusion polymorphic gesture recognition method comprises the following steps: (1) continuously capturing a gesture sequence made by a user by using Kinect; (2) the captured gesture sequence being processed by dynamic and static fusion, and the dynamic and static fusion sample sequence being obtained; (3) normalizing the dynamic and static fused sample sequence to obtain a training sample; (4) inputting the training sample into the traineddepth learning model for recognition to obtain a recognition result. The method of the invention improves the recognition rate and robustness of the polymorphic gesture, and makes the whole interactive teaching interface serve the intelligent teaching system better.

Description

Technical field [0001] The invention belongs to the field of interactive teaching, and specifically relates to a method for recognizing multi-state gestures integrating dynamic and static states. Background technique [0002] With the development of electronic technology and the emergence of electronic audio-visual equipment, the form of classrooms has gone from traditional classrooms, to electronic classrooms, multimedia classrooms, and today's smart classrooms. And more and more electronic devices are used in classrooms, This makes teachers need to continuously improve their control skills of these multimedia devices in the teaching process, even the most extensive and advanced electronic whiteboard (refer to the literature "Kong Jing, Zhao Jianhua, Liu Jialiang. Interactive electronic whiteboard supports the process of exploratory learning activities. Analysis [J]. Audio-visual Education Research, 2014, (12): 86-92+120”.), it also requires teachers to conduct contact interacti...

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): G06K9/00G06K9/62G06K9/34G06F3/01
CPCG06F3/017G06V40/113G06V40/28G06V10/267G06F18/217G06F18/214
Inventor 冯志全周晓燕
Owner UNIV OF JINAN