Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Feature extraction and three-dimensional reconstruction method of weld shape based on laser scanning

A technology of 3D reconstruction and feature extraction, applied in 3D modeling, image data processing, instruments, etc., can solve problems such as loss of information, difficulty in ensuring welding accuracy and efficiency, etc., to ensure efficiency, enhance visualization effects, and ensure accuracy Effect

Pending Publication Date: 2021-09-10
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of missing information in the image analysis process of the existing appearance inspection method, which leads to the difficulty of ensuring the accuracy and efficiency of welding, and proposes a feature extraction of weld shape based on laser scanning and 3D reconstruction methods

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
  • Feature extraction and three-dimensional reconstruction method of weld shape based on laser scanning
  • Feature extraction and three-dimensional reconstruction method of weld shape based on laser scanning
  • Feature extraction and three-dimensional reconstruction method of weld shape based on laser scanning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0039] A feature extraction and three-dimensional reconstruction method of a laser scan, a three-dimensional reconstruction method of a laser scan, a three-dimensional reconstruction method according to a laser scan, characterized in that the method is first scanned according to laser scan The principle, the optical triangulation principle design optical structure system, calculates changes in weld horizontal and vertical positions by geometric relationship; wherein the entire system is mainly formed by camera and industrial control, using CCD camera to collect image acquisition, with J1900 The industrial computer is a processing unit, and the effect of image acquisition and display is given by debugging; then, the obtained raw image is used to perform a digital form filtering, denoising, etc., for pre-processed welding, by the weld identification algorithm. The seam image is identified by feature points; finally, according to the position change of the center point of the weld im...

specific Embodiment approach 2

[0041] Unlike the specific embodiment, the characteristic extraction of the weld shape based on laser scanning and three-dimensional reconstruction method, such as figure 1 As shown, the feature extraction and the three-dimensional reconstruction method include the following steps:

[0042] Step 1. After obtaining a weld image, the model is set by the visual system, and the image coordinates of the weld image in the weld image in the image coordinate system of the weld image are converted to the camera coordinate, and transformed to the coordinate based on the robotic base coordinate system. ;

[0043] Step 2, image pretreatment;

[0044] Step three, using the Harris angle detection algorithm for feature point extraction;

[0045] Step 4, using the greedy projection triangulation algorithm for triangulation, three-dimensional reconstruction process of weld images.

specific Embodiment approach 3

[0047] Different from the specific embodiment, the characteristic extraction of the weld shape based on laser scanning, the specific process of the step one, the characteristic extraction, and the three-dimensional reconstruction method.

[0048] The visual system calibration includes the calibration of the camera, the calibration of the wire structure light plane, and the hand-grade standard;

[0049]The camera is scheduled to include two parts: the calibration of the internal parametric and the calibration of the outer parameter; the calibration of the internal parametric means that the focal length of the camera, the distortion coefficient, the calibration of the central point; the calibration of the outer parametric, refers to the rotation of the camera coordinate system and the world coordinate system Relationship between matrix and mobile matrix;

[0050] There are two ways to mark the camera: traditional camera calibration and self-calibration, self-calibration does not req...

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 feature extraction and three-dimensional reconstruction method of a weld shape based on laser scanning, and belongs to the field of image recognition. An existing appearance detection method has the problems that information is lost in the image analysis process, and welding accuracy and efficiency are difficult to guarantee. A laser scanning-based weld shape feature extraction and three-dimensional reconstruction method comprises the following steps: designing an optical structure system according to a laser scanning principle and an optical triangulation method principle, and calculating change information of horizontal and vertical positions of a weld through a geometrical relationship; preprocessing through a welding seam recognition algorithm, and performing feature point recognition on the preprocessed welding seam image; and deriving the deviation of the actual welding seam center point according to the position change of the welding seam image center point, and restoring the whole three-dimensional image after welding by performing three-dimensional reconstruction on the identified image point cloud data. The method has the advantages of high identification accuracy and high identification efficiency.

Description

Technical field [0001] The present invention relates to a feature extraction and a three-dimensional reconstruction method based on a laser-scan weld shape. Background technique [0002] At present, most companies involve welding technology during the get of the bus. In actual processing, the appearance of weld often has various defects due to the effects of processing precision and welding heat deformation. The appearance quality of the weld directly affects the reliability of the welding product, and the appearance of the weld is an effective means of improving the quality of welding forming, and the traditional method uses a two-dimensional image to analyze, which will lose many use value Information, such as width, high, distance and other information, so it is difficult to ensure the accuracy and efficiency of welding. [0003] Three-dimensional reconstruction techniques can solve such problems, and combined with the advantages of non-contact, fast, real-time, and provide te...

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): G06T17/00G06T7/80G06T7/13
CPCG06T17/00G06T7/80G06T7/13G06T2207/10004G06T2207/30152G06T2207/20164
Inventor 许景波姜宇航
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products