Method and system suitable for gesture recognition

A gesture recognition and gesture technology, applied in the field of gesture recognition, can solve a lot of problems of human, material and financial resources

Inactive Publication Date: 2020-10-16
FOSHAN UNIVERSITY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, data-driven gesture recognition methods require a large amount of high-quality, labeled sensor data to optimize the gesture recognition model, and obtaining a large amount of labeled data requires a lot of manpower, material and financial resources, and is often difficult to collect in a short period of time. enough data

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
  • Method and system suitable for gesture recognition
  • Method and system suitable for gesture recognition
  • Method and system suitable for gesture recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] A method suitable for gesture recognition such as figure 1 shown, including:

[0059] Obtain hand activity information through sensing units; that is, the first sensing unit acquires the first hand activity information, the second sensing unit acquires the second hand activity information, the third sensing unit acquires the third hand activity information, and the fourth sensing unit Obtain the fourth hand activity information; specifically: the first sensing unit is an accelerometer, and obtains hand acceleration information through the accelerometer; the second sensing unit is a gyroscope, and obtains hand angular velocity information through the gyroscope; The third sensing unit is a magnetometer, which acquires the magnetic field strength and direction information of hand activities through the magnetometer; the fourth sensing unit is a myoelectric sensor, which acquires hand myoelectric signals through the myoelectric sensor.

[0060] Send hand activity informati...

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 method suitable for gesture recognition. The method comprises the steps of acquiring hand movement information through a sensing unit; transmitting the hand activity information to a cloud service platform; establishing a gesture recognition model, and analyzing the hand movement information through the gesture recognition model to obtain a gesture recognition result; pushing the gesture recognition result to a user terminal by the cloud service platform, and controlling a corresponding device by the user terminal through an open access interface; according to the method, a gesture recognition model combining transfer learning and active learning is constructed; the problems of personalized training and cold start of a gesture recognition model are solved, knowledge of an existing gesture recognition model can be migrated to the gesture recognition model of a specific individual, and the rapid adaptive capacity and performance of the model in a new user, a newenvironment and a new scene are improved.

Description

technical field [0001] The invention relates to the research field of gesture recognition, in particular to a method and system suitable for gesture recognition. Background technique [0002] As a kind of fine-grained human behavior analysis, gesture recognition is widely used in human-computer interaction, entertainment, education, military, rehabilitation training and other fields. Its purpose is to use the computer's ability to understand gestures and execute instructions based on gestures. For example, in a smart home environment, gestures can be used to control hardware devices such as home robots and smart home appliances to improve the intelligence and naturalization of human-computer interaction; in a military environment, it can be used to assist military teaching and training, remote equipment control, etc. For automatic gesture recognition solutions, the way to obtain hand area information is the key. [0003] Currently commonly used acquisition methods can be ro...

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): G06F3/01G06K9/00G06N3/04G06N3/08
CPCG06F3/017G06F3/015G06N3/08G06F2203/011G06V40/107G06V40/11G06V40/28G06N3/045
Inventor 王爱国陈荟慧郑春弟王东朱珍
Owner FOSHAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap