Supercharge Your Innovation With Domain-Expert AI Agents!

A Gesture Recognition Method Based on Imaging Radar

A gesture recognition and imaging radar technology, applied in the field of human-computer interaction, can solve the problems of gesture recognition effect, ambient light influence, low dynamic gesture recognition rate, etc.

Active Publication Date: 2021-06-04
TSINGHUA UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a gesture recognition method based on imaging radar, to overcome the low rate of dynamic gesture recognition in the prior art, the gesture recognition effect is greatly affected by ambient light, etc., to improve the accuracy of gesture recognition

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 Gesture Recognition Method Based on Imaging Radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The gesture recognition method based on imaging radar proposed by the present invention, its flow chart is as follows figure 1 shown, including the following steps:

[0050] (1) Collect radar images of dynamic gestures to be recognized, and form a matrix A of the collected images, matrix A is a (N*S*T)*(W*H) matrix, and matrix A includes N kinds of dynamic gestures, Each dynamic gesture has S sample sequences, each sample sequence is composed of T radar images, and each radar image contains W*H pixels, where W is the width of the radar image, and H is the height of the radar image;

[0051] (2) Collect radar images of arbitrary gestures to form a matrix B. Matrix B is a matrix of M*(W*H). Among them, matrix B contains M radar images, and each radar image contains W*H Pixel, W, H are the same as in step (1), wherein W is the width of the radar image, and H is the height of the radar image;

[0052] (3) Construct a self-encoding-decoding neural network E, which specific...

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 relates to a gesture recognition method based on imaging radar. It belongs to the field of human-computer interaction. The method of the invention uses the imaging radar as the hardware carrier, and realizes high-accuracy recognition of the user's dynamic gestures in combination with the self-encoding technology and the cyclic neural network. The method can be applied to different imaging radars. Compared with the gesture recognition method based on camera equipment, the module implemented by this method is more portable, and it is not affected by the intensity of light when recognizing gestures in the environment, because it does not need a camera to shoot video, this method will not leak user privacy, It can be applied in many scenarios such as smart home appliance control and smart car cab control.

Description

technical field [0001] The invention relates to a gesture recognition method based on imaging radar, which belongs to the technical field of human-computer interaction. Background technique [0002] In recent years, gesture recognition is a research hotspot in human-computer interaction. The traditional gesture recognition method is based on the image collected by the camera. The image captured by the camera can clearly retain hand information, but the image is too large and contains a lot of data that is useless for gesture recognition. Real-time processing of camera images not only requires high hardware computing speed, but also the obtained gesture recognition results are affected by ambient light. This method cannot achieve high gesture recognition accuracy in many occasions. Moreover, since the camera will capture user images, it is easy to cause privacy issues. There are some approaches to implement gesture recognition methods using ultrasonic radar and machine lea...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/28G06N3/045G06F18/2415
Inventor 张雷张博吴沫君
Owner TSINGHUA UNIV
Features
  • R&D
  • 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