A method and system for extracting weld contour

A contour and image technology, applied in the field of image processing, can solve the problems of lack of automaticity in parameter selection and no specific solution proposed

Active Publication Date: 2021-09-14
TIANHE COLLEGE GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the welding seam extraction method can be summarized into two situations: first, the image is collected without arcing, does not contain molten pool information, and has less image noise; second, the selection of parameters in the algorithm lacks automation
[0003] For how to quickly, efficiently and clearly extract the weld contour information with large image noise, there are still many practical problems that need to be dealt with in practical applications, and no specific solutions have been proposed.

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
  • A method and system for extracting weld contour
  • A method and system for extracting weld contour
  • A method and system for extracting weld contour

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Embodiment one: refer to figure 1 , figure 2 , image 3 , Figure 4 , Figure 5 , Figure 6 , this embodiment provides a method for weld contour processing, such as figure 1 shown, including the following steps:

[0025] Step S101: Acquiring weld seam images;

[0026] Step S102: Perform threshold segmentation processing on the weld seam image according to preset conditions to obtain a threshold segmentation image;

[0027] Step S103: performing image filtering on the threshold segmented image based on a median filter method to obtain a filtered image;

[0028] Step S104: Process the filtered image based on the hough transform method to obtain a line segment set;

[0029] Step S105: According to the filter image and the line segment set, obtain the outline of the weld seam.

[0030] Wherein, performing threshold segmentation processing on the weld image according to preset conditions to obtain the threshold segmentation image includes: storing the acquired weld...

Embodiment 2

[0039] Embodiment two: refer to figure 1 , figure 2 , image 3 , Figure 4 , Figure 5 , Figure 6 , this embodiment provides a method for weld contour processing, such as figure 1 shown, including the following steps:

[0040] Step S101: Obtain a weld seam image. The weld seam image is an image including the weld seam in the welding process. In practical applications, the processing system can receive and obtain it through the image collector, or obtain it through data transmission through connection with the outside world. In the application scenario, in the robot welding system The welding seam identification or seam tracking is based on the premise of effectively extracting the seam contour information.

[0041] Step S102: Perform threshold segmentation processing on the weld seam image according to preset conditions to obtain a threshold segmentation image. The obtained weld seam image is stored in a preset current image stack, and when the stack is full, thresho...

Embodiment 3

[0087] Embodiment three: refer to figure 1 , figure 2 , image 3 , Figure 4 , Figure 5 , Figure 6 , this embodiment provides a method for weld contour processing, such as figure 1 shown, including the following steps:

[0088] Step S101: Obtain a weld seam image. The weld seam image is an image including the weld seam in the welding process. In practical applications, the processing system can receive and obtain it through the image collector, or obtain it through data transmission through connection with the outside world. In the application scenario, in the robot welding system The welding seam identification or seam tracking is based on the premise of effectively extracting the seam contour information. Compared with the two situations of welding seam image acquisition in the prior art: first, the image is collected under the condition of no arcing, does not contain molten pool information, and thus the image has less noise; second, the selection of algorithm par...

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 provides a method for weld contour processing, comprising: acquiring a weld image; performing threshold segmentation processing on the weld image according to preset conditions to obtain a threshold segmentation image; The threshold segmented image is subjected to image filtering processing to obtain a filtered image; the filtered image is processed based on the hough transform method to obtain a line segment set; and the weld seam profile is obtained according to the filtered image and the line segment set. The invention can realize dynamic, stable and accurate extraction of welding seam profile information under the condition of high image noise and high interference, thereby improving the accuracy of welding technology.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and system for extracting a weld outline. Background technique [0002] In the field of industrial welding, the number of welding workpieces is huge, the types of welds are different, and the products are complex and changeable; the quality stability of manual welding is poor and the efficiency is low. Robot welding to replace manual welding is an inevitable trend of development. The robot welding system mainly includes seam recognition and seam tracking. The effective extraction of seam contour information is the premise of seam recognition and seam tracking. At present, the weld seam extraction method can be summarized into two situations: first, the image is collected without arcing, does not contain molten pool information, and has less image noise; second, the selection of parameters in the algorithm lacks automation. [0003] For how to quickly, efficiently and cle...

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): G06T7/12G06T7/136G06T5/00
CPCG06T5/002G06T2207/20032G06T2207/20061G06T2207/30152G06T7/12G06T7/136
Inventor 汪婷
Owner TIANHE COLLEGE GUANGDONG POLYTECHNIC NORMAL UNIV
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