CN103759647A - New method for measuring geometrical features of module segmentation construction end face component - Google Patents

New method for measuring geometrical features of module segmentation construction end face component Download PDF

Info

Publication number
CN103759647A
CN103759647A CN201410042274.7A CN201410042274A CN103759647A CN 103759647 A CN103759647 A CN 103759647A CN 201410042274 A CN201410042274 A CN 201410042274A CN 103759647 A CN103759647 A CN 103759647A
Authority
CN
China
Prior art keywords
module
face
design load
image
information
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.)
Granted
Application number
CN201410042274.7A
Other languages
Chinese (zh)
Other versions
CN103759647B (en
Inventor
齐海玉
聂臆瞩
李兵
王娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TIANJIN BMESC OCEAN ENGINEERING Co Ltd
Original Assignee
TIANJIN BMESC OCEAN ENGINEERING Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by TIANJIN BMESC OCEAN ENGINEERING Co Ltd filed Critical TIANJIN BMESC OCEAN ENGINEERING Co Ltd
Priority to CN201410042274.7A priority Critical patent/CN103759647B/en
Publication of CN103759647A publication Critical patent/CN103759647A/en
Application granted granted Critical
Publication of CN103759647B publication Critical patent/CN103759647B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a new method for measuring geometrical features of a module segmentation construction end face component. The method comprises the following steps: (1) establishing an end face design value feature library of constructed modules, packaging end face design value feature information of the modules, and establishing a lookup corresponding relation between the end face design value feature information and the end face feature information of the shot modules; (2) shooting the end faces of the constructed modules, and transmitting a shot image to a computer, wherein the shot image comprises the whole feature information of the end faces needing to be recognized; (3) extracting the counter of the image by the computer, and then conducting coarse positioning on the counter of the image; (4) comparing feature information of the counter of the image with the design value information of the feature library so as to find the end face design value information of the modules, meanwhile, judging whether the modules corresponding to the counter of the image offset or rotate or not compared with the design value, and outputting the position value, needing to be readjusted, of the modules. By the adoption of the method, the reasonability of the actual postures of the modules can be judged.

Description

Module sectional construction end face member geometric properties new method of measuring
Technical field
The present invention relates to member geometric properties new method of measuring, the invention particularly relates to module sectional construction end face member geometric properties new method of measuring.
Background technology
In industry manufacture field, sometimes because fabrication is too huge, need to carry out sectional construction to buildings, for each module, in the place on border, can have a lot of pipelines and other geometric properties, docking for the ease of module, the feature of identification end face seems particularly important, and at present conventional recognition methods is measuring method, but due to the interference of the signals such as noise, make photo that optical measurement is measured can not clearly embody the actual characteristic of object, can cause the wrong identification of feature.
Summary of the invention
The object of the invention is to overcome the deficiency of prior art, a kind of module sectional construction end face member geometric properties new method of measuring of quick and precisely recognition feature is provided.
In order to achieve the above object, the technical solution used in the present invention is:
Module sectional construction end face member geometric properties new method of measuring of the present invention, it comprises the following steps:
(1) set up the end face design load feature database of the module of having built, the end face design load characteristic information of module is encapsulated and is set up the end face design load characteristic information of module and the module of shooting end face characteristic information search corresponding relation, end face design load feature database mainly comprises geometric configuration and the dimension information of module;
(2) adopt photographic equipment to take the end face of the module of having built, the image of shooting comprises the whole characteristic information of the end face of required identification, and by image transfer to computing machine;
(3) computing machine extracts image outline, then to image outline coarse positioning;
(4) according to the corresponding relation of searching of the end face characteristic information of the end face design load characteristic information of module of setting up and the module of shooting, the design load information of image outline characteristic information and feature database is compared to find to the end face design load information of module, whether can judge that the module root design load corresponding with image outline compared there is skew and has rotated simultaneously, if there is skew, according to matrix conversion, set up coordinate on image and the relation of world coordinate system, the positional value that output module need to be readjusted, until the feature in the image outline extracting is consistent with the design load information characteristics of feature database.
The invention has the beneficial effects as follows: by actual image and the image information in feature database, contrast, can obtain the specific features information of current actual object, rationality to actual module attitude judges, and actual engineer operation is had to the effect of guidance.
Accompanying drawing explanation
Accompanying drawing is the coordinate conversion schematic diagram of module sectional construction end face member geometric properties new method of measuring of the present invention.
Embodiment
Module sectional construction end face member geometric properties new method of measuring of the present invention, it comprises the following steps:
(1) set up the end face design load feature database of the module of having built, the end face design load characteristic information of module is encapsulated and is set up the end face design load characteristic information of module and the module of shooting end face characteristic information search corresponding relation, end face design load feature database mainly comprises geometric configuration and the dimension information of module;
The information of design load feature database is complicated and diversified, comprising assembly, parts (parts are also assembly in fact, artificially stipulate the sub-assemblies of general assembly part here) and part.So search extremely inconveniently, can carry out certain layout to search to various information.As a kind of implementation method of the present invention: the end face characteristic information of the end face design load characteristic information of module and the module of shooting search corresponding relation: first the end face design load feature database of module is classified by positions such as front, sides, after taking photo in certain position, can go to go to search in characteristic of correspondence storehouse according to position; In each storehouse, the information of design load feature database is divided into three grades.If assembly is one-level, form is ZP-numbering.If parts are secondary, form is BJ-numbering, if part is for LJ-numbering, is numbered ZP01-BJ01-LJ01 if give an example, and is No. 01 part of 01 work song assembly of No. 01 assembly.Certainly can also adopt the corresponding relation method of searching of other the end face design load characteristic information of module and the end face characteristic information of the module of shooting.
(2) adopt photographic equipment to take the end face of the module of having built, the image of shooting comprises the whole characteristic information of the end face of required identification, and by image transfer to computing machine;
(3) computing machine extracts image outline, then to image outline coarse positioning; The step that computing machine extraction image outline generally includes is: a. first will be to image denoising, select the denoising method of total variation, because it is a kind of non-linear Regularization method, when removing noise, having good seamed edge retention performance, is one of the effective ways in current image denoising field.B. adopt Cann yoperator carries out edge extracting; C. finally by profile, cut apart profile is cut apart, the image after can being cut apart.
To image outline coarse positioning, adopt exactly the figures such as rectangle frame that image is surrounded.
(4) according to the corresponding relation of searching of the end face characteristic information of the end face design load characteristic information of module of setting up and the module of shooting, the design load information of image outline characteristic information and feature database is compared to find to the end face design load information of module, whether can judge that the module corresponding with image outline compared with design load there is skew and has rotated simultaneously, if there is skew, according to matrix conversion, set up coordinate on image and the relation of world coordinate system, the positional value that output module need to be readjusted, until the feature in the image outline extracting is consistent with the design load information characteristics of feature database.The design load information comparison method of image outline characteristic information and feature database can be: first according to position, find after related assembly corresponding part, then find the parts that it belongs to, then continue one-level one-level and look for, until find its part feature information.
In this step, according to matrix conversion, the detailed process of setting up the relation of coordinate conversion on image is described in detail in June, 2009 Beijing Jiaotong University's Master's thesis " research of moving object position and attitude measuring system " literary composition.
As shown in Figure 1, two rectangular coordinate system in space are O t-X ty tz tand O s-X sy sz s, r in figure 0for with respect to O tposition vector, η x, η y, η zbe three axles not parallel produce draw angle, m is the inconsistent scale ratio producing of scale ratio, has following relation between them:
(r i)=r 0+(1+m)R xx)R yy)R zz)(r i) S (1)
X Y Z T = ΔX 0 Δ Y 0 Δ Z 0 ( 1 + m ) R x ( η x ) R y ( η x ) R y ( η y ) R z ( η z ) X Y Z S - - - ( 2 )
R in formula (1) xx), R yy), R zz) be the rotation matrix of three coordinate axis, because all angles are generally all very little, therefore can launch to get once item, formula (2) can be simplified:
X Y Z T = Δ X 0 Δ Y 0 Δ Z 0 + 1 η z - η y - η z 1 η x η y - η x 1 X Y Z S - - - ( 3 )
Native system is set [X, Y, Z] tfor the coordinate of module unique point in world coordinate system, [X, Y, Z] sfor the coordinate of unique point in actual object coordinate system, and in actual object, the coordinate of unique point and the pixel in photograph have relation one to one.Δ X 0, Δ Y 0, Δ Z 0, η x, η y, η zfor the side-play amount of surveyed object with respect to world coordinate system six-freedom degree.By changing the coordinate of module in world coordinate system, change the attitude that is easy to change module, adjusting module arrives correct position, and then to needing the place of recognition feature to take pictures, then compare with packaged feature contour, so repeatedly carry out, until reach the attitude needing.
Embodiment 1
(1) set up the end face design load feature database of the module of having built, the end face design load characteristic information of module is encapsulated and is set up the end face design load characteristic information of module and the module of shooting end face characteristic information search corresponding relation, design load feature database mainly comprises geometric configuration and the dimension information of module; The corresponding relation of searching of the end face characteristic information of the end face design load characteristic information of module and the module of shooting is: first the end face design load feature database of module is classified by positions such as front, sides, after taking photo in certain position, can go to go to search in characteristic of correspondence storehouse according to position; In each storehouse, the information of design load feature database is divided into three grades.If assembly is one-level, form is ZP-numbering.If parts are secondary, form is BJ-numbering, if part is for LJ-numbering, if be numbered ZP01-BJ01-LJ01, is No. 01 part of 01 work song assembly of No. 01 assembly.
(2) adopt photographic equipment to take the end face of the module of having built, the image of shooting comprises the whole characteristic information of the end face of required identification, and by image transfer to computing machine;
(3) computing machine extracts image outline, then to image outline coarse positioning;
(4) according to the corresponding relation of searching of the end face characteristic information of the end face design load characteristic information of module of setting up and the module of shooting, the design load information of image outline characteristic information and feature database is compared to find to the end face design load information of module, whether can judge that the module corresponding with image outline compared with design load there is skew and has rotated simultaneously, if there is skew, according to matrix conversion, set up coordinate on image and the relation of world coordinate system, the positional value that output module need to be readjusted, until the feature in the image outline extracting is consistent with the design load information characteristics of feature database.The design load information comparison method of image outline characteristic information and feature database is: first according to position, find after related assembly corresponding part, then find the parts that it belongs to, then continue one-level one-level and look for, until find its part feature information.
By actual image and the image information in feature database, contrast, can obtain the specific features information of current actual object, the rationality of actual works module attitude is judged, actual engineer operation is had to the effect of guidance.

Claims (1)

1. module sectional construction end face member geometric properties new method of measuring, is characterized in that it comprises the following steps:
(1) set up the end face design load feature database of the module of having built, the end face design load characteristic information of module is encapsulated and is set up the end face design load characteristic information of module and the module of shooting end face characteristic information search corresponding relation, end face design load feature database mainly comprises geometric configuration and the dimension information of module;
(2) adopt photographic equipment to take the end face of the module of having built, the image of shooting comprises the whole characteristic information of the end face of required identification, and by image transfer to computing machine;
(3) computing machine extracts image outline, then to image outline coarse positioning;
(4) according to the corresponding relation of searching of the end face characteristic information of the end face design load characteristic information of module of setting up and the module of shooting, the design load information of image outline characteristic information and feature database is compared to find to the end face design load information of module, whether can judge that the module root design load corresponding with image outline compared there is skew and has rotated simultaneously, if there is skew, according to matrix conversion, set up coordinate on image and the relation of world coordinate system, the positional value that output module need to be readjusted, until the feature in the image outline extracting is consistent with the design load information characteristics of feature database.
CN201410042274.7A 2014-01-28 2014-01-28 Module sectional construction face member geometric properties measuring method Active CN103759647B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410042274.7A CN103759647B (en) 2014-01-28 2014-01-28 Module sectional construction face member geometric properties measuring method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410042274.7A CN103759647B (en) 2014-01-28 2014-01-28 Module sectional construction face member geometric properties measuring method

Publications (2)

Publication Number Publication Date
CN103759647A true CN103759647A (en) 2014-04-30
CN103759647B CN103759647B (en) 2016-09-28

Family

ID=50526923

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410042274.7A Active CN103759647B (en) 2014-01-28 2014-01-28 Module sectional construction face member geometric properties measuring method

Country Status (1)

Country Link
CN (1) CN103759647B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105606040A (en) * 2016-01-26 2016-05-25 天津博迈科海洋工程有限公司 Large-size liquefied natural gas module attitude detection method based on three-dimensional laser detection

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005283267A (en) * 2004-03-29 2005-10-13 Suzuki Motor Corp Through hole measuring device, method, and program for through hole measurement
CN101122569A (en) * 2006-08-11 2008-02-13 欧姆龙株式会社 Method of setting reference data for inspection of solder fillets and substrate outer appearance inspection device
CN101907439A (en) * 2010-03-17 2010-12-08 中国二十二冶集团有限公司 Stimulated measurement and detection method in architectural steel structure fabrication
CN102141374A (en) * 2010-12-23 2011-08-03 苏州天准精密技术有限公司 Image type spinneret plate automatic detector
CN102749043A (en) * 2012-07-24 2012-10-24 上海中国弹簧制造有限公司 Digital photographic detection method and detection system for spring shape
CN102865823A (en) * 2012-10-12 2013-01-09 西安电子科技大学 Length measuring method based on currency

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005283267A (en) * 2004-03-29 2005-10-13 Suzuki Motor Corp Through hole measuring device, method, and program for through hole measurement
CN101122569A (en) * 2006-08-11 2008-02-13 欧姆龙株式会社 Method of setting reference data for inspection of solder fillets and substrate outer appearance inspection device
CN101907439A (en) * 2010-03-17 2010-12-08 中国二十二冶集团有限公司 Stimulated measurement and detection method in architectural steel structure fabrication
CN102141374A (en) * 2010-12-23 2011-08-03 苏州天准精密技术有限公司 Image type spinneret plate automatic detector
CN102749043A (en) * 2012-07-24 2012-10-24 上海中国弹簧制造有限公司 Digital photographic detection method and detection system for spring shape
CN102865823A (en) * 2012-10-12 2013-01-09 西安电子科技大学 Length measuring method based on currency

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105606040A (en) * 2016-01-26 2016-05-25 天津博迈科海洋工程有限公司 Large-size liquefied natural gas module attitude detection method based on three-dimensional laser detection
CN105606040B (en) * 2016-01-26 2018-01-16 天津博迈科海洋工程有限公司 Large-scale liquefied natural gas module attitude detecting method based on three-dimensional laser detection

Also Published As

Publication number Publication date
CN103759647B (en) 2016-09-28

Similar Documents

Publication Publication Date Title
CN103308925B (en) Integral three-dimensional color laser radar data point cloud generating method
Xia et al. An accurate and robust method for the measurement of circular holes based on binocular vision
CN114474056B (en) Monocular vision high-precision target positioning method for grabbing operation
CN109145471B (en) Virtual assembly system and method based on CAD and measured data co-fusion model
CN103175485A (en) Method for visually calibrating aircraft turbine engine blade repair robot
CN103425988A (en) Real-time positioning and matching method with arc geometric primitives
CN104729406A (en) Machine vision positioning method for element surface mounting
CN105005760A (en) Pedestrian re-identification method based on finite mixture model
CN105046684A (en) Image matching method based on polygon generalized Hough transform
CN112197773B (en) Visual and laser positioning mapping method based on plane information
CN110458174A (en) A kind of unordered accurate extracting method of cloud key feature points
CN103191958B (en) A kind of optical detecting method of sheet forming resilience
CN110595479B (en) SLAM track evaluation method based on ICP algorithm
US20230278198A1 (en) Method and Apparatus for Robot to Grab Three-Dimensional Object
Yi et al. Novel method for rail wear inspection based on the sparse iterative closest point method
CN103310464B (en) A kind of method of the direct estimation camera self moving parameter based on normal direction stream
CN109784297A (en) A kind of Three-dimensional target recognition based on deep learning and Optimal Grasp method
CN110472651B (en) Target matching and positioning method based on edge point local characteristic value
Hao et al. [Retracted] Fast Recognition Method for Multiple Apple Targets in Complex Occlusion Environment Based on Improved YOLOv5
Lu et al. A lightweight real-time 3D LiDAR SLAM for autonomous vehicles in large-scale urban environment
CN107328371A (en) Sub-pix contours extract based on Gaussian and the optimization using Softmax recurrence in the case where metal plate detects scene
CN103759647A (en) New method for measuring geometrical features of module segmentation construction end face component
CN106447781B (en) It is a kind of based on Minkowski and towards the collision checking method of automatic assembling
CN115719363B (en) Environment sensing method and system capable of performing two-dimensional dynamic detection and three-dimensional reconstruction
CN108168459B (en) A kind of automotive hub identification matching process

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant