Visual shape model-based robot multi-target recognition method

A shape model and recognition method technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of robot flexibility and low intelligence level, and achieve improved similarity measurement methods, optimized data structures, and high robustness sexual effect

Inactive Publication Date: 2018-01-09
WUHAN TECHN COLLEGE OF COMM
View PDF1 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the main purpose of the present invention is to address the above-mentioned problems of low flexibility and intelligence of existing robots, apply visual guidance to the field of automation, and provide a multi-target recognition method for robots based on visual shape models, aiming at realizing robot Actively identify and grab predetermined targets

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
  • Visual shape model-based robot multi-target recognition method
  • Visual shape model-based robot multi-target recognition method
  • Visual shape model-based robot multi-target recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The method of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments of the present invention.

[0065] figure 1 It is a schematic diagram of the hardware structure of the existing vision-guided robot recognition system.

[0066] Such as figure 1 As shown, the industrial camera is installed at a predetermined process position, which is the image acquisition area, and the target is sensed by the target sensor to trigger the camera to capture images. The middle interval is defined as the working area of ​​the robot, and the position information of the target in the grasping interval is obtained by the multi-target recognition algorithm and the encoder feedback of the method of the present invention, and the position coordinates are converted into the attitude control information of the robot, finally realizing the accurate grasping of the dynamic target .

[0067] figure 2 It is a schematic flow c...

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 present invention discloses a visual shape model-based robot multi-target recognition method. According to the method, the shape feature vector of a target is generated by using a polar radius with the centroid of the outline of the target adopted as a reference; and the training of a sample feature model library is completed by using a Gaussian model; dynamic time warping (DTW) is used to solve the problem of matching between feature vector elements; the principal axis parameter of the shape of the target is obtained according to a moment of inertia; and the alignment method of the starting order of the feature vectors is given. The method of the invention can identify predetermined targets under relatively complicated environments without being affected by translation, scale and rotation geometric changes and has high robustness.

Description

technical field [0001] The invention relates to machine vision recognition technology, in particular to a robot multi-target recognition method based on a visual shape model. Background technique [0002] With the continuous development of automation and artificial intelligence technology, robots based on vision guidance have been widely used in military, aerospace, medical equipment, industry and other fields. [0003] At present, in industrial production, the robot mainly controls the main body to execute instructions through pre-teaching or offline programming. Once the working conditions or the grasping target change, this method will be difficult to adapt to this dynamic change, resulting in the failure of the robot to grasp. How to correctly identify a variety of complex workpieces from the assembly line is a hot topic in the field of automation research, and the recognition algorithm is the core of visual robot guidance technology. In recent years, mainstream recogni...

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): G06K9/62G06T7/60
Inventor 周向李永贵谢计红冯贵层白成云
Owner WUHAN TECHN COLLEGE OF COMM
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