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

Robot dynamic gesture recognition method based on hidden Markov model and device thereof

A hidden Markov, dynamic gesture technology, applied in the field of human-computer interaction gesture recognition, can solve problems such as gesture interference and affect gesture recognition, and achieve the effect of reducing the amount of data storage

Pending Publication Date: 2022-01-28
HEBEI UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a robot dynamic gesture recognition method and device based on hidden Markov model to solve the problem in the prior art that gestures are easily interfered by human faces and skin-like backgrounds, which ultimately affect 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
  • Robot dynamic gesture recognition method based on hidden Markov model and device thereof
  • Robot dynamic gesture recognition method based on hidden Markov model and device thereof
  • Robot dynamic gesture recognition method based on hidden Markov model and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The purpose of human-computer interaction in the present invention is to enable the leg-arm fusion hexapod robot to understand human intentions through gestures, and then let the robot perform corresponding tasks.

[0053] The robot dynamic gesture recognition method based on the hidden Markov model of the present invention includes two modes: an offline mode and an online mode. The online mode flow chart is as follows figure 1 As shown, the offline mode flow chart is as follows figure 2 shown. Among them, the offline mode uses the test data set to test the gesture recognition results, and only realizes gesture recognition. The online mode reads the data collected by the camera installed on the robot in real time, uses the trained model to recognize gestures in real time, and sends the recognition results to the robot module to control the robot to complete specific tasks.

[0054] For the online mode, the interaction between human and robot is performed based on co...

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 robot dynamic gesture recognition method based on a hidden Markov model and a device thereof. The dynamic gesture recognition method comprises a hidden Markov model training stage and a dynamic gesture recognition stage. Both the hidden Markov model training stage and the dynamic gesture recognition stage relate to hand tracking and feature extraction; in the hand tracking process, a color histogram and particle filtering combined method is used, hand motion information is added at the same time, and the problem that the face interferes with hand tracking is solved. In the feature extraction process, in order to reduce the data storage amount, a shape context chain code is provided to describe the features of the hand motion trail. According to the method, the improved hand tracking method and the shape context chain code are combined, so that the dynamic gesture recognition is realized. The method can be used for various common robots such as wheeled robots and legged robots.

Description

technical field [0001] The invention relates to the field of human-computer interaction gesture recognition, in particular to a method and device for robot dynamic gesture recognition based on a hidden Markov model. Background technique [0002] Gesture recognition technology can be divided into two categories according to different research objects: image-based (static) and video-based (dynamic) gesture recognition. The research object of dynamic gesture recognition is the gesture motion trajectory in the image sequence corresponding to the time and space model, that is, the research object of dynamic gesture recognition is the motion trajectory with spatiotemporal characteristics, which contains both the spatial and temporal information of the gesture. The research object of static gesture recognition is an image, which only contains gesture position information. [0003] Dynamic gestures are a group of gestures that change continuously in both time and space, while stati...

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
IPC IPC(8): G06V40/20G06V10/40G06V10/75G06V10/774G06V10/84G06K9/62G06N3/00
CPCG06N3/006G06F18/22G06F18/295G06F18/214
Inventor 崔振超齐静
Owner HEBEI UNIVERSITY
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