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

Gesture recognition method and recognition device based on computer vision

A computer vision and gesture recognition technology, applied in the field of human-computer interaction, can solve the problem of low recognition accuracy, and achieve the effect of improving accuracy, improving accuracy and anti-interference, and reducing the amount of calculation.

Active Publication Date: 2019-11-15
UNIV OF SCI & TECH BEIJING
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a computer vision-based gesture recognition method and recognition device to solve the problems of low gesture positioning and recognition accuracy existing in 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 recognition method and recognition device based on computer vision
  • Gesture recognition method and recognition device based on computer vision
  • Gesture recognition method and recognition device based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 As shown, the gesture recognition method based on computer vision provided by the embodiment of the present invention

[0045] S101, collecting the hand video of the user in real time;

[0046] S102, performing target detection on each frame of image in the collected hand video through a target detection algorithm, to obtain the position and gesture state of the hand in each frame of image;

[0047] S103, according to the detected position and gesture state of the hand in each frame of image, extract the gesture features of each frame, keep the order of the gesture features in the time dimension, and obtain a feature matrix with time series features;

[0048] S104, analyzing the obtained feature matrix through the cyclic neural network, and recognizing the gesture of the user.

[0049]The gesture recognition method based on computer vision described in the embodiment of the present invention collects the user's hand video in real time; performs target...

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 recognition method and recognition device based on computer vision, capable of improving the accuracy of gesture positioning and gesture recognition and solving the problems that image information cannot be fully utilized in the gesture recognition process and time sequence characteristics are neglected under natural conditions. The gesture recognition method comprises the following steps: collecting a hand video of a user in real time; performing target detection on each frame of image in the acquired hand video through a target detection algorithm to obtain the position and gesture state of the hand in each frame of image; extracting each frame of gesture features according to the detected position and gesture state of the hand in each frame of image, andkeeping the sequence of the gesture features in time dimension to obtain a feature matrix with time sequence features; and analyzing the obtained feature matrix through a recurrent neural network, and identifying the gesture of the user. The invention relates to the field of human-computer interaction.

Description

technical field [0001] The present invention relates to the field of human-computer interaction, in particular to a gesture recognition method and recognition device based on computer vision. Background technique [0002] In the field of gesture recognition based on computer vision, there are many difficulties. The main reason is that the shape of the hand is changeable, and the sequential nature of hand movements does not only involve space issues. On the premise of only relying on image data, it is very challenging to achieve real-time gesture recognition, so real-time gesture recognition has always been a hot issue in the field of human-computer interaction. [0003] Gesture recognition under natural conditions mainly involves multiple processes such as localization, recognition and classification. In the previous solutions, many researchers used the depth camera to complete the positioning, or tried to find the hand position through the motion frame difference method co...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06V40/28G06V20/42G06N3/044
Inventor 么爱帅王忠民
Owner UNIV OF SCI & TECH BEIJING