Unlock instant, AI-driven research and patent intelligence for your innovation.

A Sub-pixel Detection Method of Curve Edge in Laser Tailored Welding Image

A technology of laser tailor welding and inspection method, applied in the field of visual inspection, can solve the problems of being easily affected by noise, the robustness needs to be improved, etc., to achieve the effect of simple selection and stable and fast calculation process

Active Publication Date: 2021-02-05
DALIAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above method can complete sub-pixel edge detection, but the process of calculating sub-pixel edges is easily affected by noise, and the robustness of detection needs to be improved

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 Sub-pixel Detection Method of Curve Edge in Laser Tailored Welding Image
  • A Sub-pixel Detection Method of Curve Edge in Laser Tailored Welding Image
  • A Sub-pixel Detection Method of Curve Edge in Laser Tailored Welding Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] This embodiment provides a sub-pixel detection method of a curve edge in an image of a laser tailor welding to-be-welded piece. The welding head used in this method is installed on the numerical control machine tool. The industrial CCD camera is installed on the welding head and moves synchronously with the welding head. Using the Sobel edge detection algorithm to obtain the pixel-level edge points (i k ,j k ), k=1,2,...n (n is the number of pixel-level edge points). Take pixel-level edge points (i k ,j k ), the specific steps to find the corresponding sub-pixel edge point are as follows:

[0039] The first step is to fit the curve with pixel-level edge points

[0040] Pixel-level edge points (i k ,j k ) is the coordinate origin O, and a coordinate system is established with the horizontal direction as the x-axis and the vertical direction as the y-axis. Take another 4 adjacent pixel-level edge points and fit the quadratic curve l k , its expression is y=a k ...

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 method for detecting sub-pixels of curve edges in images of parts to be welded by laser tailor welding, which belongs to the field of visual detection. Firstly, the image of the parts to be welded is Gaussian filtered, and a Sobel operator is used to obtain pixel-level edge points. Take the pixel-level edge point and establish a coordinate system with its center as the origin; use the pixel-level edge point and other 4 adjacent pixel-level edge points to fit the curve, and the fitting curve is translated along the y-axis; then take the pixel-level edge point as the center Take the pixels in the range of 5╳5, and after the translation, the curve divides the pixels in the range of 5╳5 into two areas, and the gray value in the area is the same; calculate the amount of curve translation from the actual gray value of the pixels in the range of 5╳5; finally Calculate the position of the sub-pixel edge point from the intersection point of the line connecting the gray center of gravity of the pixel in the 5╳5 range, the origin and the shifted curve. By selecting each pixel-level edge point in turn and repeating the above process, the sub-pixel-level edge point corresponding to each pixel-level edge point can be obtained. This method has the characteristics of fast calculation speed, high reliability and good robustness.

Description

technical field [0001] The invention belongs to the field of visual detection, in particular to a method for detecting sub-pixels of curve edges in images of parts to be welded by laser tailor welding. Background technique [0002] Tailored laser welding is a non-contact workpiece processing method, which can realize the welding of various metals and non-metals. It has the characteristics of concentrated energy density, high welding speed, small heat-affected zone, and large aspect ratio. It is more and more widely used in the manufacture of key components in the fields of marine and marine. In industrial production, the laser welding head is installed on a multi-degree-of-freedom welding robot arm or a CNC machine tool. The welding trajectory is planned before welding, and the welding head moves according to the planned trajectory during the welding process to realize the welding process. Under normal circumstances, it is necessary to use fixtures to fix the parts to be w...

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): G06T7/00G06T7/13
Inventor 王邦国
Owner DALIAN UNIV