Robot target part saliency detecting method based on vision

A technology for target parts and detection methods, applied in computer parts, instruments, manipulators, etc., can solve problems such as inability to complete tasks, and achieve the effect of complete background removal, clear effect edges, and complete target shape segmentation.

Inactive Publication Date: 2018-09-25
CHONGQING UNIV OF POSTS & TELECOMM
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in these fields, the workpiece is located on a fixed plane and placed neatly, but when the position and posture of the target part change, if the industrial robot...

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 target part saliency detecting method based on vision
  • Robot target part saliency detecting method based on vision
  • Robot target part saliency detecting method based on vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solutions in the embodiments of the present invention will be described clearly and in detail below with reference to the drawings in the embodiments of the present invention. The described embodiments are only some of the embodiments of the invention.

[0042] Some of the existing detection methods for target parts only consider the characteristics of the image itself to find the difference between the target area and the background area of ​​the image, so as to distinguish the target position from the background area. In addition, the Markov chain is used to process the saliency map, and the mutual influence relationship between the central saliency area and the surrounding background area is found. There is also a method of using the convolution of the magnitude spectrum and the filter to realize redundant information and finally find the salient area of ​​the target part. Although these methods have certain effects in detecting the salience of target ...

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 target part saliency detecting method based on vision, which belongs to the technical field of industrial robot target part detection and recognition. The method comprises the steps that a binocular vision system is calibrated; area segmentation is carried out on an original image; image processing is carried out in units of regions, and a binocular vision model is used for depth perception; the perceived depth and a color feature fusion clustering result are collaboratively processed to acquire regional depth saliency; and finally, the weighted fusion result ofglobal saliency and depth saliency is used for background suppression to complete target part detection. According to the invention, the method has the image detection effects of clear edge, completebackground rejection and complete target shape segmentation, has a good effect in the aspect of robot target part detection, makes a robot more intelligent, and can be applied to an intelligent robotsorting system.

Description

technical field [0001] The invention belongs to the technical field of detection and recognition of industrial robot target parts, and in particular relates to a vision-based detection and recognition method of robot target parts. Background technique [0002] Machine vision technology was developed in the 1960s. In 1961, the Lincoln Laboratory of the Massachusetts Institute of Technology used the camera as the input of the computer, and introduced object recognition and image processing methods into robot applications. Since then, the research on machine vision has begun. To detect the target part in the complex background, since the target part to be detected is not much different from the surrounding production environment, if the traditional threshold segmentation method is used, it is difficult to extract the salience of the target part from the complex background. Now commonly used recognition The detection methods are mainly divided into two categories: the first type...

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): G06K9/00G06K9/32G06K9/46B25J9/16
CPCB25J9/1669B25J9/1694G06V20/20G06V10/255G06V10/56
Inventor 林海波高奇峰叶川王彦博熊英俊
Owner CHONGQING UNIV OF POSTS & TELECOMM
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