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

Hand recognition method based on multi-sensor fusion technology

A multi-sensor fusion and recognition method technology, applied in the field of robot interaction, can solve the problems of real-time tracking of the position and posture of hands, recognition and tracking of hands occlusion, etc.

Active Publication Date: 2020-11-24
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the interaction of two-handed gestures, on the one hand, it simplifies the interaction process by avoiding the occlusion of two-handed gestures, and on the other hand, it uses two-dimensional images to segment and estimate gestures under occlusion, but it is difficult to track the position and posture of both hands in real time.
In view of these problems, the present invention proposes a simple multi-angle depth camera method to stably recognize the three-dimensional position and posture of both hands in any situation for a long time, which is simple to implement, easy to expand, and can effectively solve the problem of recognition and tracking of hands occlusion

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
  • Hand recognition method based on multi-sensor fusion technology
  • Hand recognition method based on multi-sensor fusion technology
  • Hand recognition method based on multi-sensor fusion technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described in detail below in conjunction with the examples, but the embodiments of the present invention are not limited to the examples. The present invention comprises the steps:

[0057] S1, adaptive low-pass filtering;

[0058] S2, multi-sensor coordinate system conversion;

[0059] S3. Adaptive weighted fusion.

[0060] Said step S1 comprises the following steps:

[0061] The basic idea of ​​the speed-based adaptive filtering algorithm is to take the weighted average of the measured value at the current moment and the filtered value at the previous moment as the filtered value at the current moment, and its weight factor changes adaptively with the current moment's motion speed.

[0062] Let the data of the position and posture of a hand be expressed as X=(x, y, z, α, β, γ) T , where the first three components (x, y, z) are the center position of the hand, and the last three components (α, β, γ) are the posture of the hand ...

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 two-hand recognition method based on multi-sensor fusion technology, which allows an operator to solve the problem of two-hand occlusion when using two-hand gestures to control a robot. The method comprises the steps of: (1) adaptive low-pass filtering; (2) multi-sensor coordinate system conversion; (3) adaptive weighted fusion. The present invention uses two kinds of sensors, which can identify the position and posture of the operator's hand, and solve the problem of vertical occlusion of both hands in the actual robot interaction application.

Description

technical field [0001] The invention belongs to the field of robot interaction, in particular to a method for recognizing both hands based on multi-sensor fusion technology. Background technique [0002] Robot human-computer interaction refers to the technology of collecting human information through some input devices, converting human intentions into instructions that robots can understand, so as to achieve dialogue between humans and robots, and then control the movement of robots. According to the different ways that humans control robots, they can be divided into gesture control, language control, expression control, brain wave signal control, etc. For the interaction of two-handed gestures, on the one hand, it simplifies the interaction process by avoiding the occlusion of two-handed gestures, and on the other hand, it uses two-dimensional images to segment and estimate gestures under occlusion, but it is difficult to track the position and posture of both hands in rea...

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): G06F3/01G06K9/00G06T3/60G06T5/00
CPCG06F3/017G06T3/604G06T2207/10028G06V40/28G06T5/70
Inventor 张平陈明轩杜广龙
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com