Image processing method for seam tracking based on laser vision
An image processing and laser technology, applied in the field of image processing, can solve the problems of long operation time of image processing algorithm and low welding seam recognition accuracy, and achieve the effect of saving memory consumption, reducing computing time and improving accuracy
Inactive Publication Date: 2020-08-14
HARBIN UNIV OF SCI & TECH
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the development of this technology is not yet mature in China, and there are shortcomings such as long operation time of image processing algorithms and low accuracy of weld seam 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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0014] Laser vision-based welding seam tracking image processing method, including five processing processes: welding seam image acquisition (1), image preprocessing (2), image threshold segmentation based on kernel density estimation (3), Hough transform line detection (4) ), weld feature point recognition (5).
[0015] Weld seam image acquisition (1) is completed by laser vision sensor. The sensor is composed of industrial CCD camera, laser emitter, optical filter and protection device, installed on the welding torch, and separated by a light barrier in the middle. The image acquisition point is 20mm in front of the welding point. It can reduce the impact of arc light, splash interference, etc. on image quality during image acquisition.
[0016] The original image of the weld seam is sent to the industrial control computer for image preprocessing (2). The spatter generated during welding is mainly manifested as isolated noise points in the image, and the median filter is ...
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
Login to View More Abstract
The invention proposes a welding-seam tracking image processing algorithm based on laser vision, including processes of image acquiring, preprocessing, threshold segmenting, welding seam characteristic identifying. A laser vision sensor acquires a welding-seam image and transmits the image to an industrial control computer where the image is processed through the following steps: first, using a median filter to eliminate the arc, the spatter and noise interference; then, using the image threshold segmenting algorithm based on kernel density to solve the optimal threshold and obtaining a binary image; and finally, using the Hough transform to detect the laser fringe lines to identify the welding-seam characteristic points and realizing real-time welding-seam tracking. Aiming at the disadvantage of the Hough transform that it is time consuming, the algorithm reduces the number of statistical parameters and reduces the computation time. The invention is suitable for V-shaped welding-seam tracking and identifying.
Description
technical field [0001] The present invention relates to the field of image processing, in particular to a method for detecting and identifying weld seam features in welding automation. Background technique [0002] Welding automation technology is widely used in industrial production due to its excellent work efficiency. It is an inevitable trend in the development of welding technology and an important means to achieve safer, more efficient and intelligent production. Real-time seam tracking, detection, and deviation correction are the keys to realize welding automation. The seam tracking technology based on laser vision has a good development prospect in the welding manufacturing industry. The laser vision sensor adopts a non-contact sensing method, which can obtain high-quality and most welded seam images, and effectively improve the sensitivity and detection accuracy of weld seam tracking. The laser light source has the advantages of high brightness and good monochroma...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/136
CPCG06T7/0004G06T2207/10004G06T2207/30152
Inventor 李东洁王世伟李潜
Owner HARBIN UNIV OF SCI & TECH