CN106971407A - A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light - Google Patents
A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light Download PDFInfo
- Publication number
- CN106971407A CN106971407A CN201710084398.5A CN201710084398A CN106971407A CN 106971407 A CN106971407 A CN 106971407A CN 201710084398 A CN201710084398 A CN 201710084398A CN 106971407 A CN106971407 A CN 106971407A
- Authority
- CN
- China
- Prior art keywords
- structure light
- image
- weld seam
- dimensional
- weld
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Abstract
A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light, comprises the following steps:(1) welding line structure light image intake and demarcation:It is scanned along target weld seam, in being spaced at a fixed time, target weld seam is shot at regular intervals, the two-dimensional structure light image of target weld seam is then obtained, by carrying out image calibration to structure light image, the physical length and width of pixel are obtained in structure light image;(2) welding line structure light image is handled:Weld seam two-dimensional structure light image is pre-processed, the extraction of axis of a weld is then carried out using the profile method of average to structure light image, the actual coordinate of each pixel of the axis of a weld is obtained;(3) by the actual coordinate of every one of axis of a weld acquired in step (2), three-dimension curved surface fitting is carried out using the interpolation method based on B battens, so as to reconstruct complete three-dimensional face of weld.Reliability of the present invention is higher, method simple, detection recognition efficiency is higher.
Description
Technical field
The present invention relates to welding robot from motion tracking field, in particular for realizing that the weld seam of view-based access control model sensing is three-dimensional
Rebuild, basis is provided for Automation of Welding.
Background technology
In the research of seam center feature is obtained using visual sensing technology, wherein monocular vision typically can only obtain
The two dimensional surface information of target weld seam, if the three-dimensional information of target weld seam to be obtained, then will utilize stereoscopic vision, commonly use
Stereo Vision mainly have binocular stereo vision and structure light vision.But most of these above-mentioned methods are both for straight
Wire bonding is stitched or small curvature weld seam, and is stitched for complicated multi-pass welding, not yet obtains the sufficient result of study of comparison, if
Using binocular stereo vision, then be accomplished by matching two images, rebuild and detection algorithm so as to add weld seam
Complexity;Or welded in real time using the method for vision guide, but be due to arc light, splashing and the electricity in welding process
Magnetic disturbance etc., the reliable detection to weld seam brings influence, therefore weld seam detection efficiency is not also high.
The content of the invention
In order to which the reliability for overcoming the shortcomings of existing weld seam three-dimensional reconstruction mode is relatively low, detection recognition efficiency is relatively low, this hair
A kind of bright reliability of offer is higher, method is simple, the detection higher weld seam Three-dimensional Gravity based on two-dimensional wire structure light of recognition efficiency
Construction method.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light, the method for reconstructing comprises the following steps:
(1) welding line structure light image intake and demarcation
It is scanned, at a fixed time in interval, target weld seam is clapped at regular intervals along target weld seam
Take the photograph, then obtain the two-dimensional structure light image of target weld seam, by carrying out image calibration to the structure light image, obtain described
The physical length and width of pixel in structure light image;
(2) welding line structure light image is handled
Weld seam two-dimensional structure light image is pre-processed, profile then is used to the pretreated structure light image
The method of average carries out the extraction of axis of a weld, obtains the actual coordinate of each pixel of the axis of a weld;
(3) by the actual coordinate of every one of axis of a weld acquired in step (2), using inserting based on B- battens
Value method carries out three-dimension curved surface fitting, so as to reconstruct complete three-dimensional face of weld.
Further, in the step (2), the extraction process for carrying out axis of a weld using the profile method of average is as follows:
Entire image is scanned by column, two edge pixels of the weld profile of each row are then found out by calculating
Point, and its average value in a column direction is obtained, the average value for each row finally obtained is constituted in weld image
Heart line, its mathematical formulae is expressed as:My=Ly=Ry, MxWith MyWhat is represented respectively is on a certain row in weld seam
The coordinate value of the pixel of heart line in the horizontal and vertical directions;LxWith LyWhat is represented respectively is weld seam top edge picture in same row
Vegetarian refreshments in the horizontal direction with the coordinate value on vertical direction;RxWith RyWhat is represented respectively is weld seam lower edge pixel in same row
In the horizontal direction with the coordinate value on vertical direction.
Further, in the step (2), the preprocessing process is as follows:
(2.1) the weld seam two-dimensional structure light image absorbed to the ccd video camera is using improved adaptive intermediate value filter
Ripple carries out denoising, and the improved adaptive median filter is the noise figure according to the noise spot of each in original image
Size carrys out the size of adaptively changing filter window, so as to reach the effect for removing noise;
(2.2) image binaryzation processing is to obtain knot of the adaptive threshold again to the process denoising using Ostu methods
Structure light image carries out binary conversion treatment.
Further, in the step (1), realizing the reconstructing system of the method for reconstructing includes robot arm, laser
Visual sensing system, the controller control connection robot arm, the laser-vision sensing system include laser diode,
Lens, optical filter and ccd video camera, the ccd video camera are fixed on the end effector of robot, the laser two
Pole pipe is fixed on the side of the ccd video camera at a certain angle, and can project the surface of workpiece to be welded, described calibrated
Journey is as follows:
(1.1) laser diode is opened, the position of the robot arm is operated and adjusted using the controller
Appearance, line laser is projected in target, the image to be calibrated that a width position is fixed is shot, wherein having one in the image to be calibrated
Steel ruler;
(1.2) scale of steel ruler in the image to be calibrated is calculated, obtains steel ruler 1cm in the image to be calibrated
The pixel count that scale is occupied;
(1.3) it is using the physical length and width calculated in the image to be calibrated representated by a pixel, i.e., complete
Into weld image demarcation.
Beneficial effects of the present invention are mainly manifested in:By entering to the weld seam two-dimensional structure light image in Fixed Time Interval
Row three-dimensional reconstruction, can obtain the higher face of weld image of integrity degree, reduce cost of labor, more stability and efficiently
Property.This technological improvement, can effectively improve the production efficiency of enterprise, while improving the competitiveness of enterprise.
Brief description of the drawings
Fig. 1 is the schematic diagram of the three-dimensional weld seam of the weld seam three-dimensional reconstruction based on two-dimensional wire structure light.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.
A kind of reference picture 1, weld seam three-dimensional rebuilding method based on two-dimensional wire structure light, the method for reconstructing includes following step
Suddenly:
(1) welding line structure light image intake and demarcation
It is scanned, at a fixed time in interval, target weld seam is clapped at regular intervals along target weld seam
Take the photograph, then obtain the two-dimensional structure light image of target weld seam, by carrying out image calibration to the structure light image, obtain described
The physical length and width of pixel in structure light image;
(2) welding line structure light image is handled
Weld seam two-dimensional structure light image is pre-processed, profile then is used to the pretreated structure light image
The method of average carries out the extraction of axis of a weld, obtains the actual coordinate of each pixel of the axis of a weld;
(3) by the actual coordinate of every one of axis of a weld acquired in step (2), using inserting based on B- battens
Value method carries out three-dimension curved surface fitting, so as to reconstruct complete three-dimensional face of weld.
The reconstructing system of the three-dimensional rebuilding method of the present embodiment, including robot arm, laser-vision sensing system are realized,
The controller control connection robot arm, the laser-vision sensing system include laser diode, lens, optical filter with
And ccd video camera, the ccd video camera is fixed on the end effector of robot, and the laser diode is with certain angle
Degree is fixed on the side of the ccd video camera, and can project the surface of workpiece to be welded.
The weld seam three-dimensional rebuilding method based on two-dimensional wire structure light of the present embodiment comprises the following steps:
(1) welding line structure light image intake and demarcation:The robot arm is operated along target using the controller
Weld seam is scanned, at a fixed time in interval, at regular intervals just using the laser-vision sensing system to target
Weld seam is shot, and obtains the two-dimensional structure light image of target weld seam, then the structure light image is demarcated;
What it was demarcated concretely comprises the following steps:
(1.1) laser diode is opened, the position of the robot arm is operated and adjusted using the controller
Appearance, line laser is projected in target, the image to be calibrated that a width position is fixed is shot, wherein having one in the image to be calibrated
Steel ruler;
(1.2) scale of steel ruler in the image to be calibrated is calculated, obtains steel ruler 1cm in the image to be calibrated
The pixel count that scale is occupied;
(1.3) it is using the physical length and width calculated in the image to be calibrated representated by a pixel, i.e., complete
Into weld image demarcation.
(2) welding line structure light image is handled:
Its welding line structure light image is handled:
(2.1) the weld seam two-dimensional structure light image absorbed to the ccd video camera is using improved adaptive intermediate value filter
Ripple carries out denoising, and the improved adaptive median filter is the noise figure according to the noise spot of each in original image
Size carrys out the size of adaptively changing filter window, so as to reach the effect for removing noise;
(2.2) described in image binaryzation processing be using Ostu methods obtain adaptive threshold again to the process denoising at
The structure light image of reason carries out binary conversion treatment;
(2.3) it is to be directed to single pixel image side to the algorithm that welding line structure light center line is extracted averagely to be come using profile
For edge, i.e., entire image is scanned by column, two edges of the weld profile of each row are then found out by calculating
Pixel, and its average value in a column direction is obtained, the average value for each row finally obtained constitutes weld image
Center line, its mathematical formulae can be expressed as:My=Ly=Ry, MxWith MyWhat is represented respectively is on a certain row
The coordinate value of the pixel of axis of a weld in the horizontal and vertical directions;LxWith LyWhat is represented respectively is in same row on weld seam
Edge pixel point in the horizontal direction with the coordinate value on vertical direction;RxWith RyWhat is represented respectively is weld seam lower edge in same row
Pixel in the horizontal direction with the coordinate value on vertical direction.
(3) weld seam three-dimensional reconstruction:To a period of time in using the laser-vision sensing system get and pass through
Data after above-mentioned image procossing carry out three-dimension curved surface fitting using the interpolation method based on B- battens, obtain complete three-dimensional weldering
Seam.
Claims (4)
1. a kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light, it is characterised in that:The method for reconstructing includes following
Step:
(1) welding line structure light image intake and demarcation
It is scanned, at a fixed time in interval, target weld seam is shot at regular intervals, so along target weld seam
The two-dimensional structure light image of target weld seam is obtained afterwards, by carrying out image calibration to the structure light image, obtains the structure
The physical length and width of pixel in light image;
(2) welding line structure light image is handled
Weld seam two-dimensional structure light image is pre-processed, it is then average using profile to the pretreated structure light image
Method carries out the extraction of axis of a weld, obtains the actual coordinate of each pixel of the axis of a weld;
(3) by the actual coordinate of every one of axis of a weld acquired in step (2), using the interpolation method based on B- battens
Three-dimension curved surface fitting is carried out, so as to reconstruct complete three-dimensional face of weld.
2. a kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light as claimed in claim 1, it is characterised in that:It is described
In step (2), the extraction process for carrying out axis of a weld using the profile method of average is as follows:
Entire image is scanned by column, then by calculating two edge pixel points of the weld profile for finding out each row,
And its average value in a column direction is obtained, the average value for each row finally obtained constitutes the center of weld image
Line, its mathematical formulae is expressed as:My=Ly=Ry, MxWith MyWhat is represented respectively is Weld pipe mill on a certain row
The coordinate value of the pixel of line in the horizontal and vertical directions;LxWith LyWhat is represented respectively is weld seam top edge pixel in same row
Point in the horizontal direction with the coordinate value on vertical direction;RxWith RyWhat is represented respectively is that weld seam lower edge pixel exists in same row
Coordinate value in horizontal direction and vertical direction.
3. a kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light as claimed in claim 1 or 2, it is characterised in that:
In the step (2), the preprocessing process is as follows:
(2.1) the weld seam two-dimensional structure light image absorbed to the ccd video camera is entered using improved adaptive median filter
Row denoising, the improved adaptive median filter is the size of the noise figure according to the noise spot of each in original image
Carry out the size of adaptively changing filter window, so as to reach the effect for removing noise;
(2.2) image binaryzation processing is to obtain structure light of the adaptive threshold again to the process denoising using Ostu methods
Image carries out binary conversion treatment.
4. a kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light as claimed in claim 1 or 2, it is characterised in that:
In the step (1), realizing the reconstructing system of the method for reconstructing includes robot arm, laser-vision sensing system, control
The device control connection robot arm, the laser-vision sensing system include laser diode, lens, optical filter and
Ccd video camera, the ccd video camera is fixed on the end effector of robot, and the laser diode is at a certain angle
The side of the ccd video camera is fixed on, and the surface of workpiece to be welded can be projected, the calibration process is as follows:
(1.1) laser diode is opened, the pose of the robot arm is operated and adjusted using the controller, will
Line laser is projected in target, the image to be calibrated that a width position is fixed is shot, wherein there is a steel in the image to be calibrated
Chi;
(1.2) scale of steel ruler in the image to be calibrated is calculated, obtains steel ruler 1cm scales in the image to be calibrated
The pixel count occupied;
(1.3) using the physical length and width calculated in the image to be calibrated representated by a pixel, that is, weldering is completed
Stitch image calibration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710084398.5A CN106971407A (en) | 2017-02-16 | 2017-02-16 | A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710084398.5A CN106971407A (en) | 2017-02-16 | 2017-02-16 | A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106971407A true CN106971407A (en) | 2017-07-21 |
Family
ID=59335125
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710084398.5A Pending CN106971407A (en) | 2017-02-16 | 2017-02-16 | A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106971407A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107631699A (en) * | 2017-08-18 | 2018-01-26 | 中北大学 | Weld seam three-dimensional appearance construction method based on network laser |
CN107876970A (en) * | 2017-12-13 | 2018-04-06 | 浙江工业大学 | A kind of robot multi-pass welding welding seam three-dimensional values and weld seam inflection point identification method |
CN107894217A (en) * | 2017-11-14 | 2018-04-10 | 中车长春轨道客车股份有限公司 | The recessed quantity measuring method of laser stitch welding weld seam based on line structure optical sensor |
CN108335286A (en) * | 2018-01-17 | 2018-07-27 | 南京理工大学 | A kind of online appearance of weld visible detection method based on double structure light |
CN108555423A (en) * | 2018-01-16 | 2018-09-21 | 中国计量大学 | Three-dimensional automatic welding line recognition device and method |
CN109239081A (en) * | 2018-09-18 | 2019-01-18 | 广东省特种设备检测研究院珠海检测院 | Weldquality parameter detection method based on structure light and visual imaging |
CN109239014A (en) * | 2018-09-05 | 2019-01-18 | 西北核技术研究所 | A kind of characteristic point acquisition methods for picture position calibration |
CN109636798A (en) * | 2018-12-24 | 2019-04-16 | 武汉大音科技有限责任公司 | A kind of three-dimensional weld inspection method based on one camera |
CN109746597A (en) * | 2017-11-08 | 2019-05-14 | 大族激光科技产业集团股份有限公司 | Using method, system and the welding equipment of camera tracking weld seam |
CN109986201A (en) * | 2018-01-03 | 2019-07-09 | 大族激光科技产业集团股份有限公司 | Tracking detection method, device, storage medium and the laser welding apparatus of weld seam |
CN111157539A (en) * | 2019-12-11 | 2020-05-15 | 华中科技大学鄂州工业技术研究院 | Weld morphology monitoring method, system and device and readable storage medium |
CN112676676A (en) * | 2020-12-16 | 2021-04-20 | 武汉逸飞激光股份有限公司 | Tab welding method |
CN113369761A (en) * | 2021-07-09 | 2021-09-10 | 北京石油化工学院 | Method and system for guiding robot welding seam positioning based on vision |
CN113427160A (en) * | 2021-06-29 | 2021-09-24 | 西安交通大学 | Self-adaptive welding method, system and equipment for welding mechanical arm and storage medium |
CN113649672A (en) * | 2021-08-06 | 2021-11-16 | 武汉理工大学 | Adaptive extraction method for geometric characteristics of butt weld |
CN114734143A (en) * | 2022-03-31 | 2022-07-12 | 苏州大学 | Weld joint tracking method based on image processing |
CN114850741A (en) * | 2022-06-10 | 2022-08-05 | 东南大学 | Welding seam recognition device and method suitable for flat plate butt welding seam |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101770641A (en) * | 2008-12-26 | 2010-07-07 | 中国科学院沈阳自动化研究所 | Rapid extracting method for structure light welding seam image characteristic points |
CN102814574A (en) * | 2012-09-06 | 2012-12-12 | 江苏科技大学 | Narrow gap welding monitoring and welding line deviation detecting method based on infrared vision sensing |
-
2017
- 2017-02-16 CN CN201710084398.5A patent/CN106971407A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101770641A (en) * | 2008-12-26 | 2010-07-07 | 中国科学院沈阳自动化研究所 | Rapid extracting method for structure light welding seam image characteristic points |
CN102814574A (en) * | 2012-09-06 | 2012-12-12 | 江苏科技大学 | Narrow gap welding monitoring and welding line deviation detecting method based on infrared vision sensing |
Non-Patent Citations (1)
Title |
---|
郑鹭斌 等: "一种基于线结构光的焊缝三维重建方法", 《激光与光电子学进展》 * |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107631699A (en) * | 2017-08-18 | 2018-01-26 | 中北大学 | Weld seam three-dimensional appearance construction method based on network laser |
CN107631699B (en) * | 2017-08-18 | 2019-07-05 | 中北大学 | Weld seam three-dimensional appearance construction method based on network laser |
CN109746597A (en) * | 2017-11-08 | 2019-05-14 | 大族激光科技产业集团股份有限公司 | Using method, system and the welding equipment of camera tracking weld seam |
CN107894217A (en) * | 2017-11-14 | 2018-04-10 | 中车长春轨道客车股份有限公司 | The recessed quantity measuring method of laser stitch welding weld seam based on line structure optical sensor |
CN107894217B (en) * | 2017-11-14 | 2020-04-10 | 中车长春轨道客车股份有限公司 | Laser stitch welding seam undercut amount detection method based on line structure light sensor |
CN107876970A (en) * | 2017-12-13 | 2018-04-06 | 浙江工业大学 | A kind of robot multi-pass welding welding seam three-dimensional values and weld seam inflection point identification method |
CN109986201B (en) * | 2018-01-03 | 2021-10-08 | 大族激光科技产业集团股份有限公司 | Tracking detection method and device for welding seam, storage medium and laser welding equipment |
CN109986201A (en) * | 2018-01-03 | 2019-07-09 | 大族激光科技产业集团股份有限公司 | Tracking detection method, device, storage medium and the laser welding apparatus of weld seam |
CN108555423A (en) * | 2018-01-16 | 2018-09-21 | 中国计量大学 | Three-dimensional automatic welding line recognition device and method |
CN108555423B (en) * | 2018-01-16 | 2024-03-15 | 中国计量大学 | Automatic three-dimensional weld joint recognition device and method |
CN108335286A (en) * | 2018-01-17 | 2018-07-27 | 南京理工大学 | A kind of online appearance of weld visible detection method based on double structure light |
CN108335286B (en) * | 2018-01-17 | 2024-03-22 | 南京理工大学 | Online weld joint forming visual detection method based on double-line structured light |
CN109239014A (en) * | 2018-09-05 | 2019-01-18 | 西北核技术研究所 | A kind of characteristic point acquisition methods for picture position calibration |
CN109239014B (en) * | 2018-09-05 | 2021-04-02 | 西北核技术研究所 | Characteristic point acquisition method for image position calibration |
CN109239081B (en) * | 2018-09-18 | 2021-01-15 | 广东省特种设备检测研究院珠海检测院 | Weld quality parameter detection method based on structured light and visual imaging |
CN109239081A (en) * | 2018-09-18 | 2019-01-18 | 广东省特种设备检测研究院珠海检测院 | Weldquality parameter detection method based on structure light and visual imaging |
CN109636798A (en) * | 2018-12-24 | 2019-04-16 | 武汉大音科技有限责任公司 | A kind of three-dimensional weld inspection method based on one camera |
CN111157539A (en) * | 2019-12-11 | 2020-05-15 | 华中科技大学鄂州工业技术研究院 | Weld morphology monitoring method, system and device and readable storage medium |
CN111157539B (en) * | 2019-12-11 | 2022-08-30 | 华中科技大学鄂州工业技术研究院 | Weld morphology monitoring method, system and device and readable storage medium |
CN112676676A (en) * | 2020-12-16 | 2021-04-20 | 武汉逸飞激光股份有限公司 | Tab welding method |
CN113427160A (en) * | 2021-06-29 | 2021-09-24 | 西安交通大学 | Self-adaptive welding method, system and equipment for welding mechanical arm and storage medium |
CN113369761A (en) * | 2021-07-09 | 2021-09-10 | 北京石油化工学院 | Method and system for guiding robot welding seam positioning based on vision |
CN113649672A (en) * | 2021-08-06 | 2021-11-16 | 武汉理工大学 | Adaptive extraction method for geometric characteristics of butt weld |
CN114734143A (en) * | 2022-03-31 | 2022-07-12 | 苏州大学 | Weld joint tracking method based on image processing |
CN114850741A (en) * | 2022-06-10 | 2022-08-05 | 东南大学 | Welding seam recognition device and method suitable for flat plate butt welding seam |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106971407A (en) | A kind of weld seam three-dimensional rebuilding method based on two-dimensional wire structure light | |
CN108637435B (en) | Three-dimensional weld tracking system and method based on vision and arc pressure sensing | |
CN210046133U (en) | Welding seam visual tracking system based on laser structured light | |
CN105783726A (en) | Curve-welding-seam three-dimensional reconstruction method based on line structure light vision detection | |
CN110153567A (en) | A kind of laser cutting system based on image recognition | |
CN106846403B (en) | Method and device for positioning hand in three-dimensional space and intelligent equipment | |
CN104978012B (en) | One kind points to exchange method, apparatus and system | |
CN109272544B (en) | Structured light three-dimensional measurement model of pipeline all-position welding line and image processing method | |
CN103500321A (en) | Visual guidance welding robot weld joint fast recognition technology based on double dynamic windows | |
EP3018632A1 (en) | Automated texturing mapping and animation from images | |
CN101833663B (en) | Binocular electronic reader | |
CN108776989A (en) | Low texture plane scene reconstruction method based on sparse SLAM frames | |
CN106713894B (en) | A kind of tracking mode stereo display method and equipment | |
CN109118544A (en) | Synthetic aperture imaging method based on perspective transform | |
CN103617631B (en) | A kind of tracking based on Spot detection | |
CN111127556B (en) | Target object identification and pose estimation method and device based on 3D vision | |
CN104596442A (en) | Assisted three-dimensional scanning device and method | |
CN109894779A (en) | A kind of machine vision tracking system and method | |
CN114241134A (en) | Virtual-real fusion three-dimensional object rapid collision detection system based on human-computer interaction | |
CN113822251A (en) | Ground reconnaissance robot gesture control system and control method based on binocular vision | |
CN104751455A (en) | Crop image dense matching method and system | |
Hermann et al. | Inclusion of a second-order prior into semi-global matching | |
CN115713794A (en) | Image-based sight line drop point estimation method and device | |
CN113134663A (en) | Laser imaging binary image preprocessing weld joint tracking method | |
CN111060091A (en) | Robot navigation system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170721 |
|
RJ01 | Rejection of invention patent application after publication |