CN101788805B - High-accuracy machine vision two-dimensional positioning method based on motion servo correction - Google Patents

High-accuracy machine vision two-dimensional positioning method based on motion servo correction Download PDF

Info

Publication number
CN101788805B
CN101788805B CN2010101034825A CN201010103482A CN101788805B CN 101788805 B CN101788805 B CN 101788805B CN 2010101034825 A CN2010101034825 A CN 2010101034825A CN 201010103482 A CN201010103482 A CN 201010103482A CN 101788805 B CN101788805 B CN 101788805B
Authority
CN
China
Prior art keywords
camera
coordinate
geometric
center coordinate
location
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.)
Expired - Fee Related
Application number
CN2010101034825A
Other languages
Chinese (zh)
Other versions
CN101788805A (en
Inventor
柳宁
王高
叶文生
王思华
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.)
Jinan University
Original Assignee
Jinan University
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 Jinan University filed Critical Jinan University
Priority to CN2010101034825A priority Critical patent/CN101788805B/en
Publication of CN101788805A publication Critical patent/CN101788805A/en
Application granted granted Critical
Publication of CN101788805B publication Critical patent/CN101788805B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention discloses a high-accuracy machine vision two-dimensional positioning method based on motion servo correction, comprising the following steps: fixedly connecting a camera to the moving machine head of equipment such as a laser cutting machine; selecting a geometric figure on a processed object as a positioning geometric characteristic; moving the camera above the positioning geometric characteristic by the motion controller of the equipment; acquiring the digital image of the positioning geometric characteristic; computing a geometric center coordinate by a template matching or edge detection method; then taking the center coordinate as the destination address of the machine head motion; moving the camera to enable the axial line of the camera to coincide with the coordinate; reacquiring the positioning geometric characteristic image, and recomputing the center coordinate; and if the deviation between the center coordinate obtained by recomputation and the current coordinate of the camera axial line is greater than an allowable value, moving the machine head again, acquiring an image and computing the center coordinate, and iterating until a satisfactory accuracy is achieved. The positioning method has high positioning accuracy and simultaneously has low performance requirements for the optical devices of the camera.

Description

A kind of high-accuracy machine vision two-dimensional positioning method based on motion servo correction
Technical field
The invention belongs to computer control field, particularly fields of numeric control technique, be specifically related to a kind of high-accuracy machine vision two-dimensional positioning method, be specially adapted to equipment such as laser cutting machine, laser marking machine based on motion servo correction.
Background technology
Machine vision adopts computer image processing technology, the geometric configuration of identifying object, and according to the geomery and the position coordinates of the proportionate relationship calculating object of the geometric properties of object and pixel.Numerical control device adds need confirm the position of workpiece in device coordinate system man-hour, and present method is artificial location and machine vision location, and artificial location efficiency is low, bigger to technical level of operators and job morale dependence; Machine vision location automaticity is high, and is when carrying out precision positioning, very high, expensive to the optical device requirement of NI Vision Builder for Automated Inspection.
Guarantee the precision of optical system, or adopt high-quality camera lens, or optical correction is carried out in the whole visual field of camera lens; To eliminate the pattern distortion of optical system; The former cost is higher, and the latter operates cumbersome, and higher to the coherence request of processing object.
Summary of the invention
The objective of the invention is to overcome the deficiency of prior art, a kind of high-accuracy machine vision two-dimensional positioning method based on motion servo correction is provided, the inventive method can obtain high-precision two-dimensional localization effect based on the optical device of general precision.
The object of the invention is realized through following technical scheme:
A kind of high-accuracy machine vision two-dimensional positioning method based on motion servo correction is accomplished by the motion head cooperation of camera, image processor, motion controller and process equipment.Camera is fixed on the motion head of process equipment, and the geometric figure on the selected workpiece is as the location geometric properties, and the motion controller drives camera arrives the precalculated position; Camera obtains the digital image information of location geometric properties; Image processor adopts template matching algorithm or the coordinate of edge detection method compute location geometric properties in viewing field of camera, obtains locating the coordinate of geometric properties in equipment through coordinate transform, and image processor sends this coordinate to the motion controller of equipment; The motion controller mobile camera; This camera axis is overlapped with the geometric center coordinate of location geometric properties, and camera obtains the image of locating geometric properties once more and calculates its geometric center coordinate, when the deviation of the current coordinate of this coordinate and camera axis during greater than allowable value; Repeat above-mentioned action, up to satisfying preset precision conditions.Image processor is taken turns the location geometric properties coordinate of calculating gained and the current location of camera axis according to last, calculates the coordinate of processing object in the machine tool coordinate system, and output.
Than prior art, advantageous effect of the present invention is following:
Generally speaking, the pattern distortion of camera lens near axis is less, and this method is utilized this principle exactly; Camera and motion head are connected firmly, and after NI Vision Builder for Automated Inspection calculated the centre coordinate of location geometric properties, mobile camera made its axis overlap with this coordinate; Again obtain image again, calculate new geometric center coordinate, iterate; The geometric center that lets the camera axis fully approach the location geometric properties with this bearing accuracy that improves NI Vision Builder for Automated Inspection, reduces the influence of optical system distortion; This method is relatively low to the optical device requirement of system, but bearing accuracy really can be very high, and great practice meaning is arranged.
Description of drawings
Fig. 1 is applied to the synoptic diagram of the specific embodiment of laser cutting machine for the present invention one;
Fig. 2 is applied to the method flow diagram of the specific embodiment of laser cutting machine for the present invention one.
Embodiment
As shown in Figure 1; Camera connects firmly on the crossbeam slide unit (motion head), and this slide unit can X and Y direction in horizontal stand move, and the geometric figure on the selected processing object is as the location geometric properties; The Position Approximate of equipment prevision location geometric properties; Above the geometric properties of location, camera obtains the digital picture of location geometric properties to the motion controller of equipment with mobile camera moving, adopts the geometric center coordinate of the method compute location geometric properties of template matches or rim detection; Again with the destination address of this centre coordinate as head motion; Mobile camera makes the camera axis overlap with this coordinate, and obtains location geometric properties image, the centre coordinate of computational geometry characteristic more again.If the location geometric properties centre coordinate and the current camera axis line coordinates deviation that recomputate gained move head again greater than allowable value, obtain image, calculate this centre coordinate, iteration like this is till reaching satisfied precision.
As shown in Figure 2, the geometric figure on the selected processing object is as the location geometric properties, and the process equipment prevision is located the position coordinates of geometric properties, and wherein, its concrete steps of method of the position coordinates of said prevision location geometric properties are:
1) the motion controller mobile camera of process equipment; The camera axis is overlapped with the coordinate of location geometric properties geometric center; Camera obtains the image of location geometric properties, adopts the geometric center coordinate of the method compute location geometric properties of template matches or rim detection;
2) a computing camera axis current position coordinates and a last step are calculated the deviation of gained geometric center coordinate, when deviation during greater than allowable value, repeating step 1) and step 2), up to deviation less than allowable value;
The geometric center coordinate transformation of last location geometric properties of taking turns is become the coordinate of processing object in machine tool and output.
As stated, can realize preferably that just the present invention, the foregoing description are merely preferred embodiment of the present invention, be not to be used for limiting practical range of the present invention; Be that all equalizations of doing according to content of the present invention change and modification, all contained by claim of the present invention scope required for protection.

Claims (1)

1. the high-accuracy machine vision two-dimensional positioning method based on motion servo correction is accomplished by the motion head cooperation of camera, image processor, motion controller and process equipment; Camera is fixed on the motion head of process equipment, and the geometric figure on the selected processing object is as the location geometric properties, and the motion controller drives camera arrives the precalculated position; (1) camera obtains the digital image information of location geometric properties; Image processor adopts template matching algorithm or the coordinate of edge detection method compute location geometric properties in viewing field of camera; Obtain locating the geometric center coordinate of geometric properties in equipment through coordinate transform; Image processor sends this geometric center coordinate the motion controller of equipment to, and the motion controller mobile camera makes the axis of this camera overlap with this geometric center coordinate of location geometric properties; (2) camera obtains the digital image information of location geometric properties once more and calculates its geometric center coordinate; When the deviation of the current coordinate of this geometric center coordinate and camera axis during greater than allowable value; Repeat the action of above-mentioned (1)-(2), up to satisfying preset precision conditions; Image processor is taken turns the geometric center coordinate of the location geometric properties that calculates gained and the current location of camera axis according to last, calculates the coordinate of processing object in the process equipment coordinate system, and output.
CN2010101034825A 2010-01-27 2010-01-27 High-accuracy machine vision two-dimensional positioning method based on motion servo correction Expired - Fee Related CN101788805B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2010101034825A CN101788805B (en) 2010-01-27 2010-01-27 High-accuracy machine vision two-dimensional positioning method based on motion servo correction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2010101034825A CN101788805B (en) 2010-01-27 2010-01-27 High-accuracy machine vision two-dimensional positioning method based on motion servo correction

Publications (2)

Publication Number Publication Date
CN101788805A CN101788805A (en) 2010-07-28
CN101788805B true CN101788805B (en) 2012-10-31

Family

ID=42532047

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2010101034825A Expired - Fee Related CN101788805B (en) 2010-01-27 2010-01-27 High-accuracy machine vision two-dimensional positioning method based on motion servo correction

Country Status (1)

Country Link
CN (1) CN101788805B (en)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102922129B (en) * 2011-08-08 2015-04-29 南京通孚轻纺有限公司 Accurate cutting method based on laser identification cutting machine
CN102331745B (en) * 2011-09-20 2013-01-09 中达电通股份有限公司 Bag making machine control system using bus-type motion controller and control method thereof
CN102773524A (en) * 2012-08-01 2012-11-14 西北工业大学 Hole making method with alignment based on machine vision
CN105136044A (en) * 2015-09-18 2015-12-09 佛山轻子精密测控技术有限公司 Workpiece height intelligent measuring apparatus and measuring method
CN105425724A (en) * 2015-11-20 2016-03-23 张碧陶 High-precision motion positioning method and apparatus based on machine vision scanning imaging
CN105269403A (en) * 2015-11-27 2016-01-27 广东工业大学 Detecting system and detecting method
CN105774268A (en) * 2016-03-21 2016-07-20 上海贝特威自动化科技有限公司 Marking positioning method for gears of automobile differentials
CN106485284B (en) * 2016-10-19 2019-05-14 哈尔滨工业大学 A kind of element localization method based on template matching
CN107609516B (en) * 2017-09-13 2019-10-08 重庆爱威视科技有限公司 Adaptive eye movement method for tracing
CN109130570B (en) * 2018-07-26 2021-01-29 广州艾德旺斯珠宝科技有限公司 Laser marking method, electronic device and storage medium
CN109570749A (en) * 2018-10-09 2019-04-05 大族激光科技产业集团股份有限公司 A method of improving laser marking system adjustment accuracy
CN110017769A (en) * 2019-03-12 2019-07-16 精诚工科汽车系统有限公司 Part detection method and system based on industrial robot
CN111612801A (en) * 2020-04-27 2020-09-01 黄河水利职业技术学院 Automatic alignment system and method for numerical control mechanical equipment

Also Published As

Publication number Publication date
CN101788805A (en) 2010-07-28

Similar Documents

Publication Publication Date Title
CN101788805B (en) High-accuracy machine vision two-dimensional positioning method based on motion servo correction
CN103846192B (en) Autonomous-positioning type intelligent dispensing system
CN111192307B (en) Self-adaptive deviation rectifying method based on laser cutting of three-dimensional part
CN102490523B (en) Automatic laser engraving system based on computer vision and service method of automatic laser engraving system
CN105619411B (en) A kind of six-shaft industrial robot palletizing method
CN108000250B (en) Casting polishing method and system
CN104552341B (en) Mobile industrial robot single-point various visual angles pocket watch position and attitude error detection method
CN110293559B (en) Installation method for automatically identifying, positioning and aligning
CN102686041A (en) Pasting method for machine vision-based irregular electronic device
EP2518663A3 (en) Object recognition method and recognition apparatus
US20180111271A1 (en) Mechanical arm positioning method and system adopting the same
CN103676976A (en) Correction method for three-dimensional worktable repositioning error
CN105323455A (en) Positioning compensation method based on machine vision
CN111223048B (en) 3D visual point cloud data splicing method and system
CN113643282A (en) Workpiece gluing track generation method and device, electronic equipment and storage medium
CN113781558B (en) Robot vision locating method with decoupling gesture and position
CN104819690A (en) Double-camera machine vision positioning method of surface mounted component
KR102634601B1 (en) Method for welding members using 3D depth sensor
CN107990825B (en) High-precision position measuring device and method based on priori data correction
CN116542914A (en) Weld joint extraction and fitting method based on 3D point cloud
CN104290102A (en) Rapid positioning compensation method
CN109373901B (en) Method for calculating center position of hole on plane
TW201521940A (en) Fixture, system and method for processing double contour
CN114434036B (en) Three-dimensional vision system for gantry robot welding of large ship structural member and operation method
CN111210392A (en) Wheel hub valve hole positioning method based on digital image processing

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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20121031

Termination date: 20170127

CF01 Termination of patent right due to non-payment of annual fee