Human skeleton point parameter acquisition device applied to humanoid motion mimicry and recognition method thereof

A technology of human body movement and human body, applied in character and pattern recognition, image data processing, instruments, etc., can solve the problems of low recognition accuracy and poor real-time performance, and achieve high recognition accuracy, strong real-time performance and strong robustness Effect

Pending Publication Date: 2017-07-25
江西制造职业技术学院
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of low recognition accuracy and poor real-time performance caused by environmental interference in posture 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
  • Human skeleton point parameter acquisition device applied to humanoid motion mimicry and recognition method thereof
  • Human skeleton point parameter acquisition device applied to humanoid motion mimicry and recognition method thereof
  • Human skeleton point parameter acquisition device applied to humanoid motion mimicry and recognition method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0010] The embodiment of the present invention figure 1 Recognition program initialization flow chart. At the beginning of the establishment of the system, it first collects every point within the field of view and forms a depth image representing the surrounding environment. The sensor generates a stream of depth images at a rate of 30 frames per second to reproduce the surrounding environment in real time. Secondly, Kinect evaluates the depth-of-field image at the pixel level to identify different parts of the human body, uses a segmentation strategy to distinguish the human body from the background environment, and obtains the depth-of-field image after kicking out the background of the tracking object. Finally, Kinect evaluates every possible pixel of the Exemplar output to determine joint points, and generates a skeletal system map based on ...

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 human skeleton point parameter acquisition device applied to humanoid motion mimicry and a recognition method thereof. The method is characterized by acquiring a depth image, recognizing human joint points by using the depth image by an OpenNI bone recognition algorithm library, extracting spatial coordinates, and providing control data for a robot controller by means of filtering, spatial vector calculation, and leg posture recognition. In view of a problem that posture recognition is influenced by environment so as to be low in recognition accuracy and poor in real-time performance, a new action recognition method based on human skeleton predefining is provided for human-machine interaction posture classification. The method give full scope to an advantage that the Kinect can obtain a depth image feature, organically combines 2bitBP characteristics, constitutes a skeleton predefined posture type, performs posture classification by using an improved support vector machine, and is good in real-time performance, high in recognition accuracy, and good in robustness in the case of illumination variation. The recognition efficiency and accuracy can meet a natural human-machine interaction system requirement.

Description

technical field [0001] The invention relates to a human body bone point parameter acquisition system and a recognition method applied to human imitation motion mimicry, which classifies and recognizes human body movements to realize humanoid robot motion mimicry. Background technique [0002] As a non-cooperative human body tracking system, Kinect can provide skeletal images, depth of field images, and can perform skeleton tracking. Through the cooperation of the depth-of-field camera and the RGB camera, Kinect can put the 3D image of the object on the screen. These characteristics of Kinect make it a popular tool for body recognition. However, relying only on depth information, there are also some defects in the recognition process: when the clothing surface is rough, the image pixels jump seriously, and the depth image is unstable; when there is occlusion or other moving objects, it cannot be accurately recognized. Aiming at these problems, the present invention proposes ...

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): G06T7/285G06K9/62
CPCG06T2207/30196G06F18/2411
Inventor 黄根勇
Owner 江西制造职业技术学院
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