CN107138431A - A kind of parts identification method for separating and system based on machine vision - Google Patents
A kind of parts identification method for separating and system based on machine vision Download PDFInfo
- Publication number
- CN107138431A CN107138431A CN201710393224.7A CN201710393224A CN107138431A CN 107138431 A CN107138431 A CN 107138431A CN 201710393224 A CN201710393224 A CN 201710393224A CN 107138431 A CN107138431 A CN 107138431A
- Authority
- CN
- China
- Prior art keywords
- parts
- classification
- big
- manipulator
- conveyer belt
- 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
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/38—Collecting or arranging articles in groups
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0063—Using robots
Abstract
The invention discloses a kind of parts identification method for separating based on machine vision and system, gather outward appearance detection and identification sorting, from two manipulators, one is used as IMAQ, another is integrated with camera and a variety of suckers, position and draw for the guiding to small parts, can be quickly and accurately positioned and capture tested part.The pick to various different sized vehicle parts can be realized, applicability is wider.And the difficulty that standard machinery hand captures programming for different parts is reduced, it is workable.
Description
Technical field
Field is recognized the present invention relates to parts, method for separating is recognized in particular to a kind of parts based on machine vision
And system.
Background technology
With developing rapidly for industry, the amount of labour is increasing.In the production process that large batch of parts are sorted, use
The quality efficiency that manpower mode carries out the sorting of parts is low and precision is not high, it is difficult to meet industrial requirements.And machine vision
Detection method then can substantially increase the automaticity of production efficiency and production with large batch of sorting parts product.
At present, the parts method of discrimination based on robot vision is predominantly in conveyer belt both sides or the industrial phase of top placement
Machine, camera advance is grabbed by the way that the parts transmitted on a moving belt are carried out with collection image of taking pictures, or by fixture, manipulator
Row is shot, then by the pretreatment and feature extraction of main control computer progress part diagram picture, and matched with ATL, so as to complete
The identification of parts species.
Domestic colleges and universities and R&D institution have for the Patents of the parts testing method based on machine vision:
The patent application " fine parts defect intelligent on-line detection method " of Application No. 201510607834.3 is used
Conveyer belt transmits parts to shooting area, then coordinates the method based on machine vision to complete detection, only with conveyer belt, fine zero
The imaging effect of part is unsatisfactory, easily causes and Lou claps or image blur;
A kind of patent application " small miniature Axle Parts size based on machine vision of Application No. 201510973877.3
On-line measuring device " moves camera to carry out shot detection to parts using removable camera pedestal, and its emphasis is list
The control of piece machine;
A kind of patent application " component surface defects detection based on machine vision of Application No. 201210124176.9
Method and device " coordinates the method based on machine vision to complete detection, only used using being shot before fixture gripping parts to camera
Fixture, has considerable restraint for the size of parts, and fixture can cause imaging to disturb.Such as need to carry out the inspection of each size parts
Survey, then need to change fixture, add cost;
A kind of patent application " multi-robot refuse classification control system " of Application No. 201610365672.1 is using biography
Send band transmission rubbish to arrive shooting area, treatment classification, after by multiple manipulators progress sorting placement, dynamic on conveyer belt shoots into
Picture, it is undesirable for the imaging effect of small rubbish.
Parts on a moving belt are only shot, for small parts, its imaging area is small by summary with camera,
Parts sideslip and the abrasion of itself, scuffing, overlap joint problems of crack that conveyer belt is present, it is easy to cause industrial camera
Small parts are leaked and clap or clap not congruent problem, at the same under conveyer belt motion state for small parts shooting effect influence compared with
Greatly.Only captured and shot to camera with mechanical paw or fixture, then need difference big for the parts of different size ranges
Small mechanical paw or fixture, adds cost.Simultaneously parts imaging area it is small, mechanical paw or fixture crawl can to its into
As interfering, damage can be also caused to component surface.
The content of the invention
The present invention is aiming at the deficiencies in the prior art are there is provided a kind of measurement and capture accurate, workable base
Method for separating and system are recognized in the parts of machine vision.
To achieve these goals, the identification method for separating of the parts based on machine vision designed by the present invention, it is special
Different part is, comprises the following steps:
S1 collecting sample part diagram pictures, carry out feature extraction to sample part diagram picture and set up parts ATL;
S2 judges whether parts to be detected reach detection zone, and judges the attribute of parts, specifically includes big
Small, magnetic and non magnetic, wherein, small parts refer to size and justify parts within formed area in a diameter of 200mm,
And weight is less than 1000N, remaining is big parts;
S3 carries out IMAQ and feature extraction to parts to be detected:Big parts directly carry out IMAQ and spy
Levy extraction;The small parts of magnetic carry out IMAQ and feature extraction after being drawn using magnetic chuck;Non magnetic small parts are adopted
IMAQ and feature extraction are carried out after being drawn with vacuum cup again;Wherein, IMAQ uses the machinery equipped with industrial camera
Hand is realized;The absorption of small parts is realized using another manipulator equipped with magnetic chuck, vacuum cup and industrial camera;
S4 is matched part diagram picture to be detected with ATL image, confirms parts species and quality;
S5 will confirm that the parts of species and quality are delivered to corresponding storing region, complete the classification of parts.
Further, it is guarantee detection quality, the sample parts and parts to be detected in the step S1 and S3
IMAQ condition and feature extraction mode all same.
Further, annular light source is additionally provided with the manipulator of IMAQ in the step S3, also for guarantor
Card detection quality.
Yet further, the detailed process of the step S5 is:Qualified big parts reach big parts with conveyer belt
Specification area, and transmitted by corresponding big parts sort pass band;Qualified small parts are directly put by another manipulator
Put;Defect ware reaches that end is reclaimed with conveyer belt.
A kind of parts identification separation system based on machine vision, it is characterized in that:Including main control computer, pass
Band, sensor, manipulator, No. two manipulators, small parts classification area, a classification are sent to push sensor, classification and push photoelectricity
Region to be detected and big parts processing region are set with sensor, big parts sort pass band, the conveyer belt, it is described
Sensor is arranged on region to be detected, and a manipulator and No. two manipulators are arranged on conveyer belt both sides, be respectively positioned on to be checked
Region is surveyed, a manipulator is used to gather parts image information, and No. two manipulators are small by zero for drawing and putting
Part;The big parts processing region is located at region downstream to be detected, and the big parts processing region includes classification and pushed
Sensor, classification push photoelectric sensor and big parts sort pass band, and the classification pushes sensor, classification and pushes photoelectricity
Sensor is arranged on conveyer belt side, and the big parts sort pass band is located at conveyer belt opposite side, and photoelectricity is pushed with classification
Sensor correspondence, the conveyer belt, sensor, manipulator, No. two manipulators, a classification push sensor and classification push light
Electric transducer is by main control computer control.
Preferably, the transmission belt end is additionally provided with parts recycling and processing device.
The advantage of the invention is that:
1st, the present invention can gather outward appearance detection and identification sorting, wherein outward appearance detection can interpolate that parts quality whether
There is problem, make up the deficiency of human eye, functional integration is high.Simultaneously this method design match mechanism, can realize to it is various not
With the pick of sized vehicle parts, applicability is wider.
2nd, the present invention is from two manipulators, and one as IMAQ, another is integrated with camera and a variety of suckers, uses
Position and draw in the guiding to small parts, can be quickly and accurately positioned and capture tested part.
3rd, the present invention is directly acquired to large parts image, and for small parts, its imaging area is small, with suction
Disk draws alignment cameras and carries out quiet shooting, and shooting effect is better than on a moving belt it being entered to take action shooting, and sucker draws zero
Part will not be imaged to it and interfere, and will not also cause crawl to damage to its surface, and reduce standard machinery hand for difference
The difficulty of parts crawl programming, it is workable.
Brief description of the drawings
Fig. 1 recognizes the overall workflow figure of method for separating for parts of the present invention based on machine vision.
Fig. 2 recognizes the integral layout structural representation of separation system for parts of the present invention based on machine vision.
Fig. 3 judges decision flow diagram for the information of the present invention.
Fig. 4 is the operating diagram differentiated to small parts.
Fig. 5 is the operating diagram differentiated to big parts.
Fig. 6 is the Local map of No. two manipulators.
In figure:Pass classification and push sensor 1, classification push photoelectric sensor 2, conveyer belt 3, parts recycling and processing device
4th, big parts sort pass band 5, robot movement regional extent 6, annular light source 7, manipulator 8, sensor 9, zero
Part 10, No. two manipulators 11, magnetic chuck 11.1, vacuum cup 11.2, No. two industrial cameras 11.3, small parts classification areas
12nd, main control computer 13.
Embodiment
The present invention is described in further detail with specific embodiment below in conjunction with the accompanying drawings:
The parts identification method for separating based on machine vision, comprises the following steps shown in figure:
S1 collecting sample part diagram pictures, carry out feature extraction to sample part diagram picture and set up parts ATL;
S2 judges whether parts to be detected reach detection zone, and judges the attribute of parts, specifically includes big
Small, magnetic and non magnetic;
S3 carries out IMAQ and feature extraction to parts to be detected:Big parts directly carry out IMAQ and spy
Levy extraction;The small parts of magnetic carry out IMAQ and feature extraction after being drawn using magnetic chuck;Non magnetic small parts are adopted
IMAQ and feature extraction are carried out after being drawn with vacuum cup again;Wherein, IMAQ uses the machinery equipped with industrial camera
Hand is realized;The absorption of small parts is realized using another manipulator equipped with magnetic chuck, vacuum cup and industrial camera.It is small by zero
Part is defined as parts of the size within the formed area of a diameter of 200mm circles, i.e. parts revolve around its geometric center
Circle formed circle area be less than a diameter of 200mm circle area, weight be less than 1000N.Remaining is defined as big by zero
Part.To ensure shooting quality, IMAQ with install annular light source additional on manipulator.
S4 is matched part diagram picture to be detected with ATL image, confirms parts species and quality;Using base
In the method for the template matches of binary image technology, a standard form Ti, figure to be identified are set up to each ATL image
As being X, in template image and images to be recognized, the foreground target pixel value after binaryzation is set to 1, and background pixel value is set to 0,
The size of template image and images to be recognized is M × N, by images to be recognized one by one with template matches, obtain its similarity Si,
For value on different images to be recognized X and standard form image Ti while the number for being the point of " 1 " is different,
So ratio Si is different.Rejection threshold value λ is set, if Si < λ, judgeIf Si >=λ, X ∈ Ti are judged.
If there are Si < λ for all templates, judge that the quality of the parts is problematic;If having for multiple template
Si >=λ, then take matching degree highest as output, completes parts species and differentiates.
S5 will confirm that the parts of species and quality are delivered to corresponding storing region, complete the classification of parts.Specifically
For:Qualified big parts reach big parts specification area with conveyer belt, and are passed by corresponding big parts sort pass band
It is defeated;Qualified small parts are directly placed by another manipulator;Defect ware reaches that end is reclaimed with conveyer belt.
Wherein, in above step S1 and S3 sample parts and the IMAQ condition and feature of parts to be detected are carried
Take mode all same.The shooting environmental condition of ATL image, illumination, shooting height are identical with input picture, small parts root
Different poses are chosen according to the difference in its face of taking a crane shot and shot one by one according to its absorption face, big parts, so that ATL
It is as detailed as possible, and ensure that the surface information that close parts have thin portion difference can be captured by camera.The seating surface of parts
It is limited, it is also on a moving belt limited for the position for shooting or drawing that can place, so for the absorption of small parts
Face, the face of taking a crane shot of big parts, all shoots one by one when preparing ATL according to different poses, as detailed as possible.Industry
The edge detection method that positioning of the camera to parts is carried using camera software kit, detects the profile side of parts substantially
After edge, it is known that its laying state, drawn or shot according to its placed side.
In the present invention, the image in ATL uses the method as input picture to carry out image preprocessing to extract figure
As feature.Image preprocessing mainly includes image enhaucament, filtering and noise reduction, image segmentation and rim detection, by image and background point
Separate out and, characteristic parameter extraction is carried out for destination object.Parts species is completed using the method for template matches to differentiate.
A kind of parts identification separation system based on machine vision, including main control computer 13, conveyer belt 3, sensor
9th, manipulator 8, No. two manipulators 11, small parts classification area 12, a classification push sensor 1, classification and push photoelectric sensing
Region to be detected and big parts processing region are set with device 2, big parts sort pass band 5, conveyer belt 3, sensor 9 is set
Put in region to be detected, a hand of machinery 8 and No. two manipulators 11 are arranged on the both sides of conveyer belt 3, are respectively positioned on region to be detected, greatly
Parts processing region is located at region downstream to be detected, and big parts processing region includes classification push sensor 1, classification and pushed
Photoelectric sensor 2 and big parts sort pass band 5, classification push sensor 1, classification push photoelectric sensor 2 and are arranged on biography
The side of band 3 is sent, big parts sort pass band 5 is located at the opposite side of conveyer belt 3, transmission corresponding with classification push photoelectric sensor 2
Band 3, sensor 9, manipulator 8, No. two manipulators 11, classification push sensors 1 and classification push photoelectric sensor 2 by
Main control computer is controlled.The termination of conveyer belt 3 is additionally provided with parts recycling and processing device 4.Equipped with industrial phase on a number manipulator 8
It is furnished with after machine, and mechanical paw on annular light source 7, No. two manipulators 11 equipped with a magnetic chuck, a vacuum cup and one
Individual industrial camera.The model ZYE1-P100/40 that the circular electromagnetic chunk of No. two manipulators 11 is selected, the big footpath of its disk is
100mm, path is 42mm, and power is 15w, and attraction is 1200N, is conducted oneself with dignity for 1900N.The model that vacuum cup is selected
ZP100HS, a diameter of 100mm of its sucker, suction cup type is heavy-load type, and material is silicon rubber.Small parts are defined as size and existed
A diameter of 200mm justifies the parts within formed area, i.e. parts and rotated a circle around its geometric center formed circle
Area be less than a diameter of 200mm circle area, weight be less than 1000N.Remaining is defined as big parts.
Invention is further elaborated using specific embodiment below, the circular electric of shown in Fig. 2 No. two manipulator 11
The model ZYE1-P100/40 that magnetic-disc is selected, the big footpath of its disk is 100mm, and path is 42mm, and power is 15w, attraction
For 1200N, conduct oneself with dignity for 1900N.The model ZP100HS that vacuum cup is selected, a diameter of 100mm of its sucker, suction cup type is
Heavy-load type, material is silicon rubber.
The working region of a number manipulator 8 and No. two manipulators 11 is the circle that radius is R, R=1m, as shown in Fig. 2 machine
Tool hands movement regional extent 6.The transfer rate of conveyer belt is 0~4m/s, and favor speed is 0.2m/s, width 400mm~
Between 800mm, length is between 3000mm~4000mm, and thickness is 10mm.The feeding interval time of the one end of conveyer belt 3 is t, t
Complete the total time required for a parts detection identification and sorting placement.Feeding time interval is set, machine can be avoided the occurrence of
Situations such as tool makees uncoordinated, missing inspection by hand.
As shown in Figures 2 and 3, on conveyer belt 3 close to manipulator end set sensor 9 with judge parts 10 size,
It is magnetic, non magnetic and whether reach region to be detected, and being accurately positioned and shooting for parts is realized by industrial camera.Specifically
Process is as follows:If being judged as big magnetic or non magnetic parts, as shown in figure 5, then using a manipulator 8 directly in transmission
To its shooting, collecting image on band 3, but heavy parts shoot multiple splicings and are identified;If being judged as small magnetic parts,
As shown in figs. 4 and 6, then it is positioned using the magnetic chuck 11.1 and No. two industrial cameras 11.3 on No. two manipulators 11
And draw, then it with the industrial camera clamped on a manipulator 8 is directed at shooting, collecting image;If being judged as small non magnetic
Parts, as shown in figs. 4 and 6, are then replaced by vacuum cup 11.2 by the magnetic chuck 11.1 on No. two manipulators 11, then right
Parts are positioned and drawn, then with the industrial camera clamped on a manipulator 8 this parts is directed at into shooting, collecting figure
Picture.
As shown in figure 1, inputting master control meter using the industrial camera shooting, collecting image on a manipulator 8 as input picture
Calculation machine 13.
Main control computer is to the image of collection from image enhaucament, filtering and noise reduction, and image is split, and the aspect of rim detection three is successively
Pre-processed, image is come out with background separation, characteristic parameter extraction is carried out for destination object.The feature master typically extracted
To include morphological feature, gray feature, textural characteristics, binary image technology can be used, i.e., put the gray value of target part
For maximum, and the gray value of background parts is set to minimum, is generally set to zero.
The shooting environmental condition of ATL image, illumination, shooting height are identical with the input picture of parts to be detected, small
Parts are chosen different poses according to the difference in its face of taking a crane shot and shot one by one according to its absorption face, big parts, so that
Make ATL as detailed as possible, and ensure that the surface information that close parts have thin portion difference can be captured by camera.ATL
In image use method as input picture to carry out image preprocessing to extract characteristics of image.
Using the method for the template matches based on binary image technology, a master die is set up to each ATL image
Plate Ti, images to be recognized is X, in template image and images to be recognized, and the foreground target pixel value after binaryzation is set to 1, the back of the body
Scape pixel value is set to 0, and their picture size size is M × N, by images to be recognized one by one with template matches, obtain its phase
Like degree Si,
For value on different images to be recognized X and standard form image Ti while the number for being the point of " 1 " is different,
So the ratio is different.Rejection threshold value λ is set, if Si < λ, judgeIf Si >=λ, X ∈ Ti are judged.If
There are Si < λ for all templates, then judge that the quality of the parts is problematic, as illustrated in fig. 1 and 2, defective in quality zero
Part is transferred directly to transmission end of tape recycling;If having Si >=λ for multiple template, matching degree highest conduct is taken
Output, completes parts species and differentiates.As shown in Figures 2 and 3, large parts directly pushes photoelectricity by the classification of transmission end of tape
Sensor and classification pusher, which coordinate, is classified, and is then delivered to storing region by big parts sort pass band.It is small-sized
Parts are then rotated a certain angle to specified identification region by the base of No. two manipulators, then by draw thereon small-sized zero
Part classification is put down.
The present invention uses a manipulator and No. two manipulator cooperatings, fast and accurately can not only guide and position
Tested part, realize it is flexible to various sizes auto parts and components open defect and precision recognition detection, while coordinating master control meter
Quick-witted energy analysis process system is calculated, intelligent decision and sorting can be carried out to the information of collection, and need not be because of element size
It is different and change different manipulator fixtures, save cost.Small parts are drawn using sucking disc type mechanical hand simultaneously
Method, both do not result in imaging interference, component surface will not also be caused crawl damage, and reduce standard machinery hand for
The difficulty of different parts crawl programmings, it is workable.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, can easily expect change or replacement, all
It should cover within the scope of the present invention.
Claims (7)
1. a kind of parts identification method for separating based on machine vision, it is characterised in that comprise the following steps:
S1 collecting sample part diagram pictures, carry out feature extraction to sample part diagram picture and set up parts ATL;
S2 judges whether parts to be detected reach detection zone, and judges the attribute of parts, specifically includes size, magnetic
And it is non magnetic, wherein, small parts refer to parts of the size within the formed area of a diameter of 200mm circles, and weight
Less than 1000N, remaining is big parts;
S3 carries out IMAQ and feature extraction to parts to be detected:Big parts directly carry out IMAQ and feature is carried
Take;The small parts of magnetic carry out IMAQ and feature extraction after being drawn using magnetic chuck;Non magnetic small parts are using true
Suction disk carries out IMAQ and feature extraction again after drawing;Wherein, IMAQ uses the manipulator equipped with industrial camera real
It is existing;The absorption of small parts is realized using another manipulator equipped with magnetic chuck, vacuum cup and industrial camera;
S4 is matched part diagram picture to be detected with ATL image, confirms parts species and quality;
S5 will confirm that the parts of species and quality are delivered to corresponding storing region, complete the classification of parts.
2. the parts identification method for separating according to claim 1 based on machine vision, it is characterised in that:The step
The IMAQ condition and feature extraction mode all same of sample parts and parts to be detected in S1 and S3.
3. the parts identification method for separating according to claim 2 based on machine vision, it is characterised in that:The step
In S3 annular light source is additionally provided with the manipulator of IMAQ.
4. the parts identification method for separating according to claim 3 based on machine vision, it is characterised in that:The step
S5 detailed process is:Qualified big parts reach big parts specification area with conveyer belt, and by corresponding big parts
Sort pass band is transmitted;Qualified small parts are directly placed by another manipulator;Defect ware reaches that end is entered with conveyer belt
Row is reclaimed.
5. a kind of parts identification separation system based on machine vision, it is characterised in that:Including main control computer, conveyer belt,
Sensor, manipulator, No. two manipulators, small parts classification area, a classification push sensor, classification and push photoelectric sensing
Region to be detected and big parts processing region, the sensing are set with device, big parts sort pass band, the conveyer belt
Device is arranged on region to be detected, and a manipulator and No. two manipulators are arranged on conveyer belt both sides, are respectively positioned on area to be detected
Domain a, manipulator is used to gather parts image information, and No. two manipulators are used to drawing and putting small parts;
The big parts processing region is located at region downstream to be detected, and the big parts processing region includes classification and pushes sensing
Device, classification push photoelectric sensor and big parts sort pass band, and the classification pushes sensor, classification and pushes photoelectric sensing
Device is arranged on conveyer belt side, and the big parts sort pass band is located at conveyer belt opposite side, and photoelectric sensing is pushed with classification
Device correspondence, the conveyer belt, sensor, manipulator, No. two manipulators, a classification push sensor and classification push photoelectric transfer
Sensor is by main control computer control.
6. the parts identification separation system according to claim 5 based on machine vision, it is characterised in that:The transmission
Belt end is additionally provided with parts recycling and processing device.
7. the parts identification separation system according to claim 5 based on machine vision, it is characterised in that:Described No. one
It is provided with manipulator on industrial camera, No. two manipulators and is provided with magnetic chuck, vacuum cup and industrial camera.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710393224.7A CN107138431B (en) | 2017-05-27 | 2017-05-27 | A kind of components identification method for separating and system based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710393224.7A CN107138431B (en) | 2017-05-27 | 2017-05-27 | A kind of components identification method for separating and system based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107138431A true CN107138431A (en) | 2017-09-08 |
CN107138431B CN107138431B (en) | 2019-11-08 |
Family
ID=59780854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710393224.7A Active CN107138431B (en) | 2017-05-27 | 2017-05-27 | A kind of components identification method for separating and system based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107138431B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107570430A (en) * | 2017-10-26 | 2018-01-12 | 中国人民解放军国防科技大学 | Intelligent robot-based part sorting method in mechanical equipment maintenance process |
CN107671008A (en) * | 2017-11-13 | 2018-02-09 | 中国科学院合肥物质科学研究院 | A kind of part stream waterline automatic sorting boxing apparatus of view-based access control model |
CN107831176A (en) * | 2017-12-04 | 2018-03-23 | 苏州斯莱克精密设备股份有限公司 | A kind of elongated soft part detection device |
CN107886496A (en) * | 2017-09-30 | 2018-04-06 | 北京得华机器人技术研究院有限公司 | A kind of quality determining method of the auto-parts based on form fit |
CN108176607A (en) * | 2017-12-13 | 2018-06-19 | 全椒祥瑞塑胶有限公司 | A kind of injecting products quality efficient detection method |
CN108480240A (en) * | 2018-03-19 | 2018-09-04 | 李晓 | A kind of pearl intelligent sorting system based on machine vision |
CN109013375A (en) * | 2018-05-31 | 2018-12-18 | 郑州轻工业学院 | A kind of electric power tower angle steels detection device and detection method |
CN109746931A (en) * | 2019-03-13 | 2019-05-14 | 厦门中高智能电器科学研究院有限公司 | A kind of polymorphic type foreign matter removing robot towards GIS cavity |
CN109927030A (en) * | 2019-03-28 | 2019-06-25 | 云南国土资源职业学院 | A kind of robot visual orientation method of appearance components detection |
CN110308151A (en) * | 2019-07-22 | 2019-10-08 | 重庆大学 | A kind of surface of workpiece defect identification method and device based on machine vision |
CN111366584A (en) * | 2020-04-09 | 2020-07-03 | 安徽科技学院 | Method and equipment for classifying damage of recyclable parts of scraped car based on visual identification |
CN111553445A (en) * | 2020-05-20 | 2020-08-18 | 北京三一智造科技有限公司 | Part identification method, device, storage medium and electronic equipment |
CN112699743A (en) * | 2020-12-15 | 2021-04-23 | 黄冈格罗夫氢能汽车有限公司 | System for identifying hydrogen energy fuel cell vehicle indicator lamp and button switch by one key |
CN112707162A (en) * | 2020-12-17 | 2021-04-27 | 东莞市李群自动化技术有限公司 | Feeding method and multi-channel feeding machine |
CN113510132A (en) * | 2020-04-10 | 2021-10-19 | 广东鸿山环境集团有限公司 | Intelligent garbage treatment and classification system |
CN114455312A (en) * | 2021-12-27 | 2022-05-10 | 广州优尼冲压有限公司 | Replaceable visual discharging system |
CN115945404A (en) * | 2023-02-15 | 2023-04-11 | 苏州天准科技股份有限公司 | Defect detection equipment and detection method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4678920A (en) * | 1985-06-17 | 1987-07-07 | General Motors Corporation | Machine vision method and apparatus |
CN202516964U (en) * | 2011-12-22 | 2012-11-07 | 浙江金刚汽车有限公司 | Plate element procedure turning mechanical hand |
CN102974551A (en) * | 2012-11-26 | 2013-03-20 | 华南理工大学 | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy |
CN103706575A (en) * | 2013-12-31 | 2014-04-09 | 江苏大学 | Device and method for grading and sorting lenses on line based on two-stage image acquisition |
CN105953138A (en) * | 2015-12-31 | 2016-09-21 | 广东工业大学 | Machine vision light source device with light spot shape controllable and implementing method thereof |
CN205600756U (en) * | 2016-04-28 | 2016-09-28 | 扬州大学 | Optic platform snatchs manipulator |
CN106216256A (en) * | 2016-07-04 | 2016-12-14 | 佛山科学技术学院 | A kind of air spring rod multiple position automatic checkout equipment |
-
2017
- 2017-05-27 CN CN201710393224.7A patent/CN107138431B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4678920A (en) * | 1985-06-17 | 1987-07-07 | General Motors Corporation | Machine vision method and apparatus |
CN202516964U (en) * | 2011-12-22 | 2012-11-07 | 浙江金刚汽车有限公司 | Plate element procedure turning mechanical hand |
CN102974551A (en) * | 2012-11-26 | 2013-03-20 | 华南理工大学 | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy |
CN103706575A (en) * | 2013-12-31 | 2014-04-09 | 江苏大学 | Device and method for grading and sorting lenses on line based on two-stage image acquisition |
CN105953138A (en) * | 2015-12-31 | 2016-09-21 | 广东工业大学 | Machine vision light source device with light spot shape controllable and implementing method thereof |
CN205600756U (en) * | 2016-04-28 | 2016-09-28 | 扬州大学 | Optic platform snatchs manipulator |
CN106216256A (en) * | 2016-07-04 | 2016-12-14 | 佛山科学技术学院 | A kind of air spring rod multiple position automatic checkout equipment |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107886496A (en) * | 2017-09-30 | 2018-04-06 | 北京得华机器人技术研究院有限公司 | A kind of quality determining method of the auto-parts based on form fit |
CN107570430B (en) * | 2017-10-26 | 2018-07-31 | 中国人民解放军国防科技大学 | Intelligent robot-based part sorting method in mechanical equipment maintenance process |
CN107570430A (en) * | 2017-10-26 | 2018-01-12 | 中国人民解放军国防科技大学 | Intelligent robot-based part sorting method in mechanical equipment maintenance process |
CN107671008A (en) * | 2017-11-13 | 2018-02-09 | 中国科学院合肥物质科学研究院 | A kind of part stream waterline automatic sorting boxing apparatus of view-based access control model |
CN107831176B (en) * | 2017-12-04 | 2023-10-27 | 苏州斯莱克精密设备股份有限公司 | Slender soft part detection device |
CN107831176A (en) * | 2017-12-04 | 2018-03-23 | 苏州斯莱克精密设备股份有限公司 | A kind of elongated soft part detection device |
CN108176607A (en) * | 2017-12-13 | 2018-06-19 | 全椒祥瑞塑胶有限公司 | A kind of injecting products quality efficient detection method |
CN108480240A (en) * | 2018-03-19 | 2018-09-04 | 李晓 | A kind of pearl intelligent sorting system based on machine vision |
CN109013375A (en) * | 2018-05-31 | 2018-12-18 | 郑州轻工业学院 | A kind of electric power tower angle steels detection device and detection method |
CN109746931A (en) * | 2019-03-13 | 2019-05-14 | 厦门中高智能电器科学研究院有限公司 | A kind of polymorphic type foreign matter removing robot towards GIS cavity |
CN109927030A (en) * | 2019-03-28 | 2019-06-25 | 云南国土资源职业学院 | A kind of robot visual orientation method of appearance components detection |
CN110308151A (en) * | 2019-07-22 | 2019-10-08 | 重庆大学 | A kind of surface of workpiece defect identification method and device based on machine vision |
CN111366584B (en) * | 2020-04-09 | 2023-01-03 | 安徽科技学院 | Method and equipment for classifying damage of recyclable parts of scraped car based on visual identification |
CN111366584A (en) * | 2020-04-09 | 2020-07-03 | 安徽科技学院 | Method and equipment for classifying damage of recyclable parts of scraped car based on visual identification |
CN113510132A (en) * | 2020-04-10 | 2021-10-19 | 广东鸿山环境集团有限公司 | Intelligent garbage treatment and classification system |
CN111553445A (en) * | 2020-05-20 | 2020-08-18 | 北京三一智造科技有限公司 | Part identification method, device, storage medium and electronic equipment |
CN111553445B (en) * | 2020-05-20 | 2024-04-19 | 北京三一智造科技有限公司 | Component identification method and device, storage medium and electronic equipment |
CN112699743A (en) * | 2020-12-15 | 2021-04-23 | 黄冈格罗夫氢能汽车有限公司 | System for identifying hydrogen energy fuel cell vehicle indicator lamp and button switch by one key |
CN112707162A (en) * | 2020-12-17 | 2021-04-27 | 东莞市李群自动化技术有限公司 | Feeding method and multi-channel feeding machine |
CN114455312A (en) * | 2021-12-27 | 2022-05-10 | 广州优尼冲压有限公司 | Replaceable visual discharging system |
CN115945404A (en) * | 2023-02-15 | 2023-04-11 | 苏州天准科技股份有限公司 | Defect detection equipment and detection method |
CN115945404B (en) * | 2023-02-15 | 2023-06-27 | 苏州天准科技股份有限公司 | Defect detection equipment and detection method |
Also Published As
Publication number | Publication date |
---|---|
CN107138431B (en) | 2019-11-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107138431B (en) | A kind of components identification method for separating and system based on machine vision | |
CN110314854B (en) | Workpiece detecting and sorting device and method based on visual robot | |
CN106204614B (en) | A kind of workpiece appearance defects detection method based on machine vision | |
CN106000904B (en) | A kind of house refuse Automated Sorting System | |
CN106824816B (en) | A kind of detection of PE bottle and method for sorting based on machine vision | |
CN105891233B (en) | Lens surface defect intelligent checking system and its implementation based on machine vision | |
CN105690393A (en) | Four-axle parallel robot sorting system based on machine vision and sorting method thereof | |
CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
CN106583268A (en) | PE bottle inspecting and sorting system based on machine vision | |
CN101561948A (en) | Automatic coin quality detection device | |
CN106802301A (en) | The machine vision on-line detecting system and method for a kind of engine valve | |
CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
CN105478529B (en) | Full-automatic stamping line products surface quality on-line detecting system and method | |
CN110763700A (en) | Method and equipment for detecting defects of semiconductor component | |
CN202133624U (en) | Automatic detection device of unqualified magnet ring | |
Yunardi | Contour-based object detection in Automatic Sorting System for a parcel boxes | |
CN106680293A (en) | Machine vision based motor rotor gib defect detection system and method | |
CN108582075A (en) | A kind of intelligent robot vision automation grasping system | |
CN113744247A (en) | PCB welding spot defect identification method and system | |
CN114346821A (en) | Workpiece processing method and system and readable storage medium | |
CN207081666U (en) | A kind of zipper detecting device based on machine vision | |
CN111330874A (en) | Detection device and detection method for pollution or impurity defects of bottom area of medicine bottle | |
CN206490044U (en) | A kind of solar battery sheet surface defects detection system | |
CN113715012A (en) | Automatic assembly method and system for remote controller parts | |
CN113602799A (en) | Airport luggage case carrying system and control method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |