Nothing Special   »   [go: up one dir, main page]

CN107150032A - A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method - Google Patents

A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method Download PDF

Info

Publication number
CN107150032A
CN107150032A CN201610125496.4A CN201610125496A CN107150032A CN 107150032 A CN107150032 A CN 107150032A CN 201610125496 A CN201610125496 A CN 201610125496A CN 107150032 A CN107150032 A CN 107150032A
Authority
CN
China
Prior art keywords
workpiece
image acquisition
pick
computer
sorting
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
CN201610125496.4A
Other languages
Chinese (zh)
Other versions
CN107150032B (en
Inventor
蒋知峰
方江龙
吕燕
张力
蒋劲峰
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.)
Shanghai Electric Group Corp
Original Assignee
Shanghai Electric Group Corp
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 Shanghai Electric Group Corp filed Critical Shanghai Electric Group Corp
Priority to CN201610125496.4A priority Critical patent/CN107150032B/en
Publication of CN107150032A publication Critical patent/CN107150032A/en
Application granted granted Critical
Publication of CN107150032B publication Critical patent/CN107150032B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B07SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00Sorting 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
    • B07C5/34Sorting according to other particular properties
    • B07C5/342Sorting according to other particular properties according to optical properties, e.g. colour
    • B07C5/3422Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B07SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07CPOSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00Sorting 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
    • B07C5/02Measures preceding sorting, e.g. arranging articles in a stream orientating

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Manipulator (AREA)

Abstract

The present invention relates to a kind of workpiece identification based on many image acquisition equipments and sorting equipment, including the first image acquisition equipment, the second image acquisition equipment, work handling device, pick device and computer, the work handling device is used in one direction be conveyed workpiece;Described first image obtains the upstream that equipment is located at the work handling device, the image for obtaining all workpiece positioned at work handling device upstream;The device that picks picks the workpiece on work handling device according to the control of the computer;Second image acquisition equipment is located at the downstream of the work handling device, and the topography for the single workpiece that device is picked is picked for obtaining;The computer is used to calculate picking the time, picking position and off-position for each workpiece.The invention further relates to a kind of workpiece identification based on many image acquisition equipments and method for sorting.The present invention can ensure identification range and accuracy of identification simultaneously when carrying out workpiece identification.

Description

A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method
Technical field
The present invention relates to workpiece identification and Sorting Technique field, more particularly to a kind of workpiece based on many image acquisition equipments is known Not with sorting equipment and method.
Background technology
Workpiece sorting, pickup, carrying based on machine vision are obtained in production fields such as machinery, food, medicine, cosmetics To increasingly extensive application.In these production lines, multiple workpiece mixing are sent to off-sorting station, undertake sorting, the dress carried The workpiece in off-sorting station can be recognized by putting requirement, carried or put to desired position by procedure calls after pickup.Patent " is based on machine The robot sorting system and method for device vision " (the middle institute of ship heavy industry 716, CN103706568A) obtains static using one camera Circular tablets image after sorted by mechanical hand by shape, the error range for drawing position and article physical location is 0.2mm. Patent " the robot automatic stacking of view-based access control model processing " (Shenyang University of Technology, CN104058260A) is for being in off-sorting station Static workpiece obtains image by single camera, workpiece geometry barycenter is obtained after image processing, then pressed by robot palletizer This barycenter, which is drawn, completes stacking.Patent " industrial robot sorting system " (Shenyang University of Technology, CN204036474U) is used The motion of single camera, obtain two diverse locations image, by binocular stereo vision algorithm obtain workpiece geometry barycenter and Implement crawl for robot in placing direction, locus of the generation workpiece in off-sorting station." one kind is used for robot and carried patent The vision positioning method of operation " (Shanghai Co., Ltd of FANUC robots, CN101637908A) is raising robot feeding Attitude accuracy, for the single workpiece on fixed position before crawl by one 2 dimension camera obtain position compensation data, pick up Posture feature offset data is obtained by a 3-dimensional camera after taking, this method is mainly used in solving blank part in irregular shape The precision problem of feeding clamping.
In the patent of above-mentioned use single camera, in order to obtain multiple workpiece images in a visual field, unless using expensive High resolution camera, pixel is enough, and the measurement accuracy otherwise obtained by image procossing is not high.
Above-mentioned application is directed to single layer workpieces occasion, the off-sorting station for only accommodating single layer workpieces tiling, in the production line having Because there is new workpiece to continue to flow into, mutually pushed between workpiece in off-sorting station, each workpiece can make slow translation and rotate, In timeslice before the crawls such as image procossing, moving track calculation after image acquisition, the existing small change of the location of workpiece.In reality Trickle displacement can also be occurred relative to position before by applying the absorption picked or thing being crawled in clamping jaw tightening process.It is above-mentioned special Profit is not included in these change in location, it is impossible to ensure positioning precision.
In addition, can not be realized in the scheme of above-mentioned use one camera it is multiple pick device, such as robot co-ordination.Pick It is less efficient, and camera utilization rate also than relatively low, increase picks device and certainly will cause being multiplied for camera quantity.And Camera is not only increased if the scheme being imaged twice for the scope of different identifications using single camera needs frequent become The extra cost that focal length is brought is changed, but also has badly influenced the efficiency picked." one kind is used for robot and carries work patent In the vision positioning method of industry ", First 2D cameras are fixed on robot arm, are moved to after robot grabbing workpiece another Position compensation and positioning are carried out under the 3D cameras that one position is fixed.This method is in the application scenario of multiple robots The quantity of camera, which can be caused, to be multiplied.The service efficiency of camera can not be given full play to.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of workpiece identification based on many image acquisition equipments and sorting equipment And method, carry out that during workpiece identification identification range and accuracy of identification can be ensured simultaneously, solve for being continued to flow on production line Influence of the change in displacement that workpiece is produced in the time difference for recognizing and capturing to precision.
The technical solution adopted for the present invention to solve the technical problems is:A kind of workpiece based on many image acquisition equipments is provided to know Not and sorting equipment, including the first image acquisition equipment, the second image acquisition equipment, work handling device, pick device and Computer, the work handling device is used in one direction be conveyed workpiece;Described first image obtains equipment and is located at The upstream of the work handling device, the image for obtaining all workpiece positioned at work handling device upstream;It is described to pick Device picks the workpiece on work handling device according to the control of the computer;Second image acquisition equipment is located at The downstream of the work handling device, the topography for the single workpiece that device is picked is picked for obtaining;The computer For calculating picking the time, picking position and off-position for each workpiece, the computer obtains with the first image set respectively Standby, the second image acquisition equipment, work handling device and pick device connection.
Position and workpiece transmitting device translational speed when the computer is identified according to each workpiece calculate and pick dress Put and the time and pick position for picking for each workpiece.
The positional information calculation for the workpiece location feature that the computer is obtained always according to second image acquisition equipment is gone to work Part position correction compensation rate, and the target location discharged according to workpiece calculates the off-position of workpiece.
The workpiece location feature refers to not picked the shape or wheel at the position that device is blocked in the one side that workpiece is picked Profile.
The device that picks carries out picking workpiece by way of absorption or crawl.
It is industrial camera that described first image, which obtains equipment and the second image acquisition equipment,.Preferably, the camera resolution It is less than or equal to 1920*2560 no more than 5,000,000 pixels, or pel array.
The sensor being connected with computer is additionally provided with the work handling device, the sensor is used to detect workpiece transmission dress The transmission position put and/or speed.
The device that picks is two or more, and the quantity of second image acquisition equipment is less equal than the number for picking device Amount, device and second image acquisition equipment of picking is arranged in the spaced downstream of work handling device.
The device that picks is two or more, and the device that picks avoids interference with collision on mobile route.
The technical solution adopted for the present invention to solve the technical problems is:A kind of workpiece based on many image acquisition equipments is provided to know Not and method for sorting, comprise the following steps:
(1) first image acquisition equipment obtains the image for including multiple workpiece of work handling device upstream, and carries out image Processing, identifies the information transfer of first position for the workpiece to be picked to computer;
(2) computer control picks the second place that device navigates to workpiece, waits workpiece to pick work when reaching the second place Part;
The location feature that (3) second image acquisition equipments pick workpiece to picking device carries out IMAQ, by image Processing obtains workpiece location feature relative to the positional information for picking device;
(4) computer controls to pick device positioning according to obtained workpiece location feature relative to the positional information for picking device Workpiece is discharged to off-position.
Also include between the step (1) and step (2) computer according to first position of each workpiece when identified and Work handling device translational speed, which is calculated, picks device for the step of picking time and the second place of each workpiece.
Step (4) Computer goes out according to obtained workpiece location feature relative to the positional information calculation for picking device Pick the compensation rate of the target location of device release workpiece.
The location feature of the step (3) refers to the shape for not picked the position that device is blocked in the one side that workpiece is picked Shape or contour line.
The step (3) is specially that IMAQ and gray threshold processing are carried out to picked workpiece, extracts contour line, And the coordinate of angle point and the corner of contour line are obtained, amount of bias is obtained by angular coordinate, obtained by the corner of contour line Angle offset amount.
It is described pick device for two or more when, in step (2), Computer controls multiple devices that pick to navigate to work respectively The second place of part, waits workpiece to pick workpiece when reaching the second place, then multiple devices that pick are moved to the second figure successively In acquisition region as obtaining equipment;Multiple devices that pick avoid interference with collision on mobile route.
In order to improve the efficiency of identification and sorting, the device that picks for first completing to pick workpiece is first moved to the second image acquisition equipment Acquisition region in.
Described when picking device for two or more, the quantity of second image acquisition equipment is less equal than the number for picking device Amount, each second image acquisition equipment at least corresponds to one and picks device, is controlled respectively in step (2) Computer multiple The second place that device navigates to workpiece is picked, waits workpiece to pick workpiece when reaching the second place, it is then multiple to pick device In the acquisition region for being moved to each self-corresponding second image acquisition equipment.
Beneficial effect
As a result of above-mentioned technical scheme, the present invention compared with prior art, has the following advantages that and good effect:
The present invention can be realized using polyphaser and the high accuracy of a wide range of article is recognized and picked, and solve phase in conventional method Contradiction between machine identification range and camera resolution.
First camera in the present invention obtains the sorting information of workpiece and can carry out the positional information that workpiece is picked.Picking work Part is simultaneously completed before positioning measurement, and workpiece real space position is different from the locus that identification measurement is obtained, and is contained identification and is shone To movement of the workpiece before gear grips or complete adhesive during the movement for capturing workpiece in this period, and crawl after phase Or skew.Different workpiece location features is different, and fine positioning measurement is carried out by second camera by the location feature of institute's grabbing workpiece, Because the size of workpiece location feature is smaller, higher image measurement precision is can obtain in second camera imaging, simultaneously because Device is picked between the workpiece that is captured there is no relative motion, therefore the positioning letter of the current workpiece of enough accuracy can be obtained Breath.Therefore removed present invention can apply to the sorting of workpiece in the off-sorting station of the multiple workpiece mixing of the multi items continued to flow into and positioning Fortune, thus solve due to the workpiece continued to flow on production line recognize and capture time difference produce change in displacement to essence The influence of degree, realizes high efficiency and high-precision robotic article sorting operation.
Camera used in the present invention is the industrial camera of common specification, no in resolution ratio and performance particularly Ask.Therefore, the holistic cost of the present invention program is relatively low.
First camera and second camera used in the present invention arrange in the upstream and downstream of workpiece transmitting device respectively, so The work of two cameras does not influence mutually, it is possible to achieve the lasting of mutual cooperation, efficient work.First camera is carried out The workpiece of workpiece area carries out global identification, so that the effect of overall coordination is realized, multiple pickers in transmitting device downstream The position for multiple workpiece that structure and second camera can be recognized according to first camera is picked to workpiece simultaneously, improves work Efficiency.
Under using multiple service conditions picked device, multiple pick device can share the collection result of first camera.Together When, in the case of the position rational deployment to picking device, second camera can be used alternatingly by multiple pick device.This Sample whole device minimized camera usage quantity while improved efficiency, improves the utilization rate of camera, reduces implementation Cost.
Brief description of the drawings
Fig. 1 is the apparatus structure schematic diagram of the present invention;
Fig. 2 is the top view of the present invention;
Fig. 3 is the system block diagram of the present invention;
Fig. 4 is the workflow diagram of the present invention;
Fig. 5 is the identification region schematic diagram of the first image acquisition equipment in the embodiment of the present invention;
Fig. 6 is the identification region schematic diagram of the second image acquisition equipment in the embodiment of the present invention;
Fig. 7 is correction-compensation amount schematic diagram in the embodiment of the present invention.
Embodiment
With reference to specific embodiment, the present invention is expanded on further.It should be understood that these embodiments be merely to illustrate the present invention and It is not used in limitation the scope of the present invention.In addition, it is to be understood that after the content of the invention lectured has been read, people in the art Member can make various changes or modifications to the present invention, and these equivalent form of values equally fall within the application appended claims and limited Scope.
The present invention relates to a kind of workpiece identification based on many image acquisition equipments and sorting equipment, as depicted in figs. 1 and 2, bag Include the first image acquisition equipment 1, the second image acquisition equipment 2, work handling device 5, pick device 3 and computer 6, The work handling device 5 is used in one direction be conveyed workpiece 4;Described first image obtains equipment 1 and is located at institute The upstream of work handling device 5 is stated, the image for obtaining all workpiece positioned at the upstream of work handling device 5;It is described to pick Device 3 is taken to pick the workpiece 4 on work handling device 5 according to the control of the computer;Second image is obtained Equipment 2 is located at the downstream of the work handling device 5, and the Local map for the single workpiece that device 3 is picked is picked for obtaining Picture;The computer 6 is used to calculate picking the time, picking position and off-position for each workpiece, 6 points of the computer Not with the first image acquisition equipment 1, the second image acquisition equipment 2, work handling device 5 and picking device 3 and being connected.Institute The sensor 7 for being additionally provided with and being connected with computer 6 on work handling device 5 is stated, the sensor 7 is used to detect that workpiece is transmitted The transmission position of device and/or speed.The both sides of whole workpiece identification and sorting equipment are additionally provided with workpiece and pile up area 8, the workpiece It is the off-position for picking device 3 to pile up area 8.
Wherein, computer can be calculated and picked according to position of each workpiece when identified and workpiece transmitting device translational speed Device is taken the time and to pick position for picking for each workpiece;Computer can also be obtained according to the second image acquisition equipment The positional information calculation of workpiece location feature go out workpiece position correction compensation rate, and the target location discharged according to workpiece is calculated Go out the off-position of workpiece, the high accuracy of a wide range of article is recognized and picked so as to realize.First image acquisition equipment and Two image acquisition equipments can use the industrial camera of common specification.
It is seen that, the present invention can be realized using many image acquisition equipments and the high accuracy of a wide range of article is recognized and picked, Solve the contradiction between camera identification range and camera resolution in conventional method.The first image acquisition equipment in the present invention Obtain the sorting information of workpiece and the positional information that workpiece is picked can be carried out.Before picking workpiece and completing positioning measurement, work Part real space position is different from identification measurement obtained locus, contains after identification image is obtained to capturing this period Movement or skew of the workpiece before gear grips or complete adhesive during the movement of interior workpiece, and crawl.Different workpiece Location feature is different, fine positioning measurement is carried out by the second image acquisition equipment by the location feature of institute's grabbing workpiece, due to workpiece The size of location feature is smaller, and higher image measurement precision is can obtain in the imaging of the second image acquisition equipment, simultaneously because Device is picked between the workpiece that is captured there is no relative motion, therefore the positioning letter of the current workpiece of enough accuracy can be obtained Breath.Therefore removed present invention can apply to the sorting of workpiece in the off-sorting station of the multiple workpiece mixing of the multi items continued to flow into and positioning Fortune, thus solve due to the workpiece continued to flow on production line recognize and capture time difference produce change in displacement to essence The influence of degree, realizes high efficiency and high-precision robotic article sorting operation.
Image acquisition equipment used in the present invention can be the industrial camera of common specification, not have in resolution ratio and performance There is special requirement.Therefore, the holistic cost of the present invention program is relatively low.The first image acquisition equipment used in the present invention Arranged respectively in the upstream and downstream of workpiece transmitting device with the second image acquisition equipment, the work of two such image acquisition equipment Work does not influence mutually, it is possible to achieve the lasting of mutual cooperation, efficient work.First image acquisition equipment carries out workpiece The workpiece in region carries out global identification, so as to realize the effect of overall coordination, transmitting device downstream it is multiple pick device and The position for multiple workpiece that second image acquisition equipment can be recognized according to the first image acquisition equipment is picked workpiece simultaneously Take, improve operating efficiency.
The invention further relates to a kind of workpiece identification based on many image acquisition equipments and method for sorting, as shown in Figure 3 and Figure 4, Comprise the following steps:First image acquisition equipment obtains the image for including multiple workpiece of work handling device upstream, and carries out Image procossing, identifies the information transfer of first position for the workpiece to be picked to computer;Computer control picks device The second place of workpiece is navigated to, waits workpiece to pick workpiece when reaching the second place;Second image acquisition equipment is to picking dress The location feature for putting picked workpiece carries out IMAQ, and workpiece location feature is obtained relative to picking device by image procossing Positional information;Computer picks device according to obtained workpiece location feature relative to the positional information control for picking device to be determined Position discharges workpiece to off-position.Computer obtains transmission position and/or the speed of work handling device by sensor, with complete Into whole workflow.Wherein, the identification region of the first image acquisition equipment is as shown in figure 5, dotted line frame 9 is the first figure Identification region as obtaining equipment, the identification region of the second image acquisition equipment are as shown in fig. 6, dashed circle 10 is the The identification region of two image acquisition equipments, its part overlapping with workpiece 4 is location feature 11.
This method is further described below by three specific embodiments.
Embodiment one:
Workpiece transmitting device is conveyer belt, and pick device is an articulated robot, and workpiece is casing.First camera and Two cameras use the industrial camera of common specification, and its resolution ratio is 5,000,000 pixels.Conveyer belt is driven by electric rotating machine, Rotary encoder is installed on motor, the motor anglec of rotation is detected, computer is by constantly reading the goniometer of encoder feedback Calculate the displacement and speed of conveyer belt.
First camera is fixedly mounted on the surface of conveyor belt workpieces approach axis upstream, and camera lens is vertical downwardly directed to off-sorting station Domain, second camera is one and is fixedly mounted on the surface of conveyer belt downstream workpiece sorting area, and camera lens is vertical downwardly directed to Sorting area,
A) first camera gathers the image comprising multiple workpiece of conveyer belt upstream and carries out image procossing, identifies and wants The information transfer of the position of the workpiece picked is to computer;
B position and conveyer belt translational speed when) computer is identified according to each workpiece calculate robot and are directed to Picking for each workpiece and picks position at the time;
C) computer-controlled robot, which navigates to pick when position waits workpiece arrival to pick position, picks workpiece, Ran Houyi Move the lower section of second camera;
D) second camera picks the location feature progress IMAQ of workpiece to robot, and work is obtained by image procossing Part location feature is relative to the positional information for picking device;
E) computer according to the workpiece location feature obtained in previous step relative to the positional information calculation for picking device Go out to pick the compensation rate of the target location of device release workpiece, so as to obtain the release that the robot workpiece to be discharged piles up area Position;
F) computer-controlled robot navigates to the off-position release workpiece that workpiece piles up area;
G) repeat step C is all picked until workpiece.
Wherein step D) in second camera be that the contour line for being picked an angle at the upward face edge of casing is positioned Feature recognition.The contour line at one, casing edge angle is carried out at IMAQ and gray threshold under specific illumination condition Reason, extracts contour line, and obtains the coordinate of angle point and the corner of contour line, sees Fig. 7.Obtained by the coordinate of angle point Amount of bias X ' and Y '.Angle offset amount α ' is obtained by the corner of two contour lines.X ', Y ' and α ' numerical value are sent to Computer, and calculate the revised location of workpiece parameter X, Y and α.Dotted line frame is the position after workpiece correction in Fig. 7 Put.
Embodiment two:
Workpiece transmitting device is conveyer belt, and pick device is two articulated robots, second camera also for two and respectively with The position of two robots is corresponding.Workpiece is casing.First camera and second camera use the industrial camera of common specification, Its pel array is 1920*2560.Conveyer belt is driven by electric rotating machine, and motor speed is constant, and computer is turned by motor The displacement and speed of fast setup algorithm conveyer belt.
First camera is fixedly mounted on the surface of conveyor belt workpieces approach axis upstream, and camera lens is vertical downwardly directed to off-sorting station Domain, second camera is fixedly mounted on the surface of conveyer belt downstream workpiece sorting area, and camera lens is vertical downwardly directed to sorting area,
Two articulated robots and two second cameras are arranged in the spaced downstream certain distance of conveyer belt, mutually non-interference,
A) first camera gathers the image comprising multiple workpiece of conveyer belt upstream and carries out image procossing, identifies and wants The information transfer of the position of the workpiece picked is to computer;Wherein, computer calculates work according to the mobile status of workpiece conveyor The displacement of part, and pass through before first camera has recognized that workpiece leaves first camera image acquisition region with workpiece conveyor First camera again identifies that follow-up workpiece;
B position and conveyer belt translational speed when) computer is identified according to each workpiece calculate robot and are directed to Picking for each workpiece and picks position at the time;
C) computer controls the position that picks of two robot localizations to two different workpiece to wait workpiece to reach respectively Workpiece is picked when picking position and then the lower section of each self-corresponding second camera is moved respectively to;
D) second camera picks the location feature progress IMAQ of workpiece to Liang Tai robots respectively, at image Reason obtains workpiece location feature relative to the positional information for picking device;
E) computer according to the workpiece location feature obtained in previous step relative to the positional information calculation for picking device Go out to pick the compensation rate of the target location of device release workpiece, so that obtaining the Liang Tai robots workpiece to be discharged piles up area Off-position;
F) computer controls two robot localizations to discharge workpiece to the off-position that workpiece piles up area respectively;
G) repeat step C is all picked until workpiece.
Second camera is to carry out positioning spy to being picked the contour line at an angle at the upward face edge of casing in wherein step D Levy identification.IMAQ is carried out to the contour line at one, casing edge angle under specific illumination condition and gray threshold is handled, Contour line is extracted, and obtains the coordinate of angle point and the corner of contour line, Fig. 7 is seen.Biasing is obtained by the coordinate of angle point Measure X ' and Y '.Angle offset amount α ' is obtained by the corner of two contour lines.Send X ', Y ' and α ' numerical value to calculating Machine, and calculate the revised location of workpiece parameter X, Y and α.Dotted line frame is the position after workpiece correction in Fig. 7.
Embodiment three:
Workpiece transmitting device is conveyer belt, and it is two articulated robots to pick device, and second camera is one.Workpiece is case Body.First camera and second camera use the industrial camera of common specification, and its pel array is 1920*2560.Conveyer belt Driven by electric rotating machine, rotary encoder is installed on motor, detect the motor anglec of rotation, computer is by constantly reading The displacement and speed of the angle calculation conveyer belt of encoder feedback.
First camera is fixedly mounted on the surface of conveyor belt workpieces approach axis upstream, and camera lens is vertical downwardly directed to off-sorting station Domain, second camera is fixedly mounted on the surface of conveyer belt downstream workpiece sorting area, and camera lens is vertical downwardly directed to sorting area,
Two articulated robots are arranged in the spaced downstream certain distance of conveyer belt, mutually non-interference, and second camera is located at two Between platform robot,
A) first camera gathers the image comprising multiple workpiece of conveyer belt upstream and carries out image procossing, identifies and wants The information transfer of the position of the workpiece picked is to computer;Wherein, computer calculates work according to the mobile status of workpiece conveyor The displacement of part, and pass through before first camera has recognized that workpiece leaves first camera image acquisition region with workpiece conveyor First camera again identifies that follow-up workpiece;
B position and conveyer belt translational speed when) computer is identified according to each workpiece calculate robot and are directed to Picking for each workpiece and picks position at the time;
C) computer-controlled robot, which navigates to pick when position waits workpiece arrival to pick position, picks workpiece, Ran Houyi Move the lower section of second camera;
D) second camera picks the location feature progress IMAQ of workpiece to robot, and work is obtained by image procossing Part location feature is relative to the positional information for picking device;
E) computer according to the workpiece location feature obtained in previous step relative to the positional information calculation for picking device Go out to pick the compensation rate of the target location of device release workpiece, so as to obtain the release that the robot workpiece to be discharged piles up area Position;
F) computer-controlled robot navigates to the off-position release workpiece that workpiece piles up area;
G) repeat step C is all picked until workpiece.
In order to improve the efficiency of identification and sorting, the robot for first completing to pick workpiece is first moved to the lower section of second camera, after Complete to pick workpiece picks the lower section that second camera is moved to after device, carries out successively.When First robot has performed step Another robot starts simultaneously at execution step C during rapid C.Liang Tai robots should avoid interference with collision on mobile route.
Second camera is to carry out positioning spy to being picked the contour line at an angle at the upward face edge of casing in wherein step D Levy identification.IMAQ is carried out to the contour line at one, casing edge angle under specific illumination condition and gray threshold is handled, Contour line is extracted, and obtains the coordinate of angle point and the corner of contour line, Fig. 7 is seen.Biasing is obtained by the coordinate of angle point Measure X ' and Y '.Angle offset amount α ' is obtained by the corner of two contour lines.Send X ', Y ' and α ' numerical value to calculating Machine, and calculate the revised location of workpiece parameter X, Y and α.Dotted line frame is the position after workpiece correction in Fig. 7.
As can be seen here, under using multiple service conditions picked device, multiple pick device can share adopting for first camera Collect result.Meanwhile, in the case of the position rational deployment to picking device, second camera can be by multiple friendships that pick device For using.So whole device minimized camera usage quantity while improved efficiency, improves the utilization rate of camera, Reduce the cost of implementation.

Claims (18)

1. a kind of workpiece identification and sorting equipment based on many image acquisition equipments, including the first image acquisition equipment, the second image Obtain equipment, work handling device, pick device and computer, it is characterised in that the work handling device is used for Workpiece is conveyed in one direction;Described first image obtains the upstream that equipment is located at the work handling device, Image for obtaining all workpiece positioned at work handling device upstream;The device that picks is according to the computer Control picks the workpiece on work handling device;Second image acquisition equipment is located at the work handling device Downstream, pick the topography of the single workpiece that device is picked for obtaining;The computer is used to calculate each Workpiece picks the time, picks position and off-position;The computer respectively with the first image acquisition equipment, second Image acquisition equipment, work handling device and pick device connection.
2. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute State position when computer is identified according to each workpiece and workpiece transmitting device translational speed calculates and picks device pin Time and position is picked to picking for each workpiece.
3. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute The positional information calculation for stating the workpiece location feature that computer is obtained always according to second image acquisition equipment goes out workpiece position Rectification building-out amount is put, and the target location discharged according to workpiece calculates the off-position of workpiece.
4. workpiece identification and sorting equipment according to claim 3 based on many image acquisition equipments, it is characterised in that institute Workpiece location feature is stated to refer to not picked the shape or profile at the position that device is blocked in the one side that workpiece is picked Line.
5. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute State pick device draw or crawl by way of carry out picking workpiece.
6. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute It is industrial camera to state the first image acquisition equipment and the second image acquisition equipment.
7. workpiece identification and sorting equipment according to claim 6 based on many image acquisition equipments, it is characterised in that institute The resolution ratio for stating industrial camera is no more than 5,000,000 pixels, or pel array is less than or equal to 1920*2560.
8. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute The sensor for being additionally provided with and being connected with computer on work handling device is stated, the sensor is used to detect work handling device Transmission position and/or speed.
9. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute State and pick device for two or more, the quantity of second image acquisition equipment is less equal than the quantity for picking device, Device and second image acquisition equipment of picking is arranged in the spaced downstream of work handling device.
10. workpiece identification and sorting equipment according to claim 1 based on many image acquisition equipments, it is characterised in that institute State and pick device for two or more, the device that picks avoids interference with collision on mobile route.
11. a kind of workpiece identification and method for sorting based on many image acquisition equipments, it is characterised in that comprise the following steps:
(1) first image acquisition equipment obtains the image for including multiple workpiece of work handling device upstream, and carries out at image Reason, identifies the information transfer of first position for the workpiece to be picked to computer;
(2) computer control picks the second place that device navigates to workpiece, waits workpiece to pick workpiece when reaching the second place;
The location feature that (3) second image acquisition equipments pick workpiece to picking device carries out IMAQ, at image Reason obtains workpiece location feature relative to the positional information for picking device;
(4) computer picks device relative to the positional information control for picking device according to obtained workpiece location feature and navigated to Off-position discharges workpiece.
12. workpiece identification and method for sorting according to claim 11 based on many image acquisition equipments, it is characterised in that institute Stating also includes first position when computer is identified according to each workpiece and work between step (1) and step (2) Part conveyer translational speed, which is calculated, picks device for the step of picking time and the second place of each workpiece.
13. workpiece identification and method for sorting according to claim 11 based on many image acquisition equipments, it is characterised in that institute Step (4) Computer is stated to go out to pick relative to the positional information calculation for picking device according to obtained workpiece location feature The compensation rate of the target location of device release workpiece.
14. workpiece identification and method for sorting according to claim 11 based on many image acquisition equipments, it is characterised in that institute State step (3) location feature refer to the shape for not picked the position that device is blocked in the one side that workpiece is picked or Contour line.
15. workpiece identification and method for sorting according to claim 11 based on many image acquisition equipments, it is characterised in that institute It is specially that IMAQ and gray threshold processing are carried out to picked workpiece to state step (3), extracts contour line, and obtain The coordinate of angle point and the corner of contour line are obtained, amount of bias is obtained by angular coordinate, the corner for passing through contour line is obtained Angle offset amount.
16. workpiece identification and method for sorting according to claim 11 based on many image acquisition equipments, it is characterised in that institute State pick device for two or more when, in step (2), Computer controls multiple devices that pick to navigate to workpiece respectively The second place, waits workpiece to pick workpiece when reaching the second place, then multiple devices that pick are moved to the second figure successively In acquisition region as obtaining equipment;Multiple devices that pick avoid interference with collision on mobile route.
17. workpiece identification and method for sorting according to claim 16 based on many image acquisition equipments, it is characterised in that first The device that picks for completing to pick workpiece is first moved in the acquisition region of the second image acquisition equipment.
18. workpiece identification and method for sorting according to claim 11 based on many image acquisition equipments, it is characterised in that institute State when picking device for two or more, the quantity of second image acquisition equipment is less equal than the quantity for picking device; Each second image acquisition equipment at least corresponds to one and picks device, and in step (2), Computer controls multiple pick respectively Take device to navigate to the second place of workpiece, wait workpiece to pick workpiece when reaching the second place, it is then multiple to pick dress Put and be moved in the acquisition region of each self-corresponding second image acquisition equipment.
CN201610125496.4A 2016-03-04 2016-03-04 Workpiece identification and sorting device and method based on multi-image acquisition equipment Active CN107150032B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610125496.4A CN107150032B (en) 2016-03-04 2016-03-04 Workpiece identification and sorting device and method based on multi-image acquisition equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610125496.4A CN107150032B (en) 2016-03-04 2016-03-04 Workpiece identification and sorting device and method based on multi-image acquisition equipment

Publications (2)

Publication Number Publication Date
CN107150032A true CN107150032A (en) 2017-09-12
CN107150032B CN107150032B (en) 2020-06-23

Family

ID=59791877

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610125496.4A Active CN107150032B (en) 2016-03-04 2016-03-04 Workpiece identification and sorting device and method based on multi-image acquisition equipment

Country Status (1)

Country Link
CN (1) CN107150032B (en)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107597600A (en) * 2017-09-26 2018-01-19 北京京东尚科信息技术有限公司 Sorting system and method for sorting
CN108993929A (en) * 2018-08-01 2018-12-14 穆科明 A kind of dual-machine linkage industrial machine vision automatic checkout system
CN109352626A (en) * 2018-11-05 2019-02-19 佛山市奇创智能科技有限公司 The equipment and method of robot crawl object
CN109513629A (en) * 2018-11-14 2019-03-26 深圳蓝胖子机器人有限公司 Packages method, apparatus and computer readable storage medium
CN109513630A (en) * 2018-11-14 2019-03-26 深圳蓝胖子机器人有限公司 Packages system and its control method, storage medium
CN109772733A (en) * 2019-01-15 2019-05-21 西安交通大学 A kind of the defect bamboo block detection sorting equipment and method of view-based access control model
CN110294316A (en) * 2019-06-04 2019-10-01 深圳蓝胖子机器人有限公司 Method, system and the equipment of article on a kind of crawl conveyer belt
KR20190120463A (en) * 2018-04-13 2019-10-24 삼성디스플레이 주식회사 Apparatus for transferring panel and method for transferring panel
CN111112108A (en) * 2019-12-30 2020-05-08 上海交通大学 Hull plate cutting part sorting equipment and method
CN111167731A (en) * 2019-10-23 2020-05-19 武汉库柏特科技有限公司 Product sorting method, product sorting system and intelligent sorting robot
CN111283685A (en) * 2020-03-05 2020-06-16 广州市斯睿特智能科技有限公司 Vision teaching method of robot based on vision system
CN112024426A (en) * 2020-09-01 2020-12-04 北京智通云联科技有限公司 Multi-station visual identification system
CN112623759A (en) * 2020-12-18 2021-04-09 中国建材国际工程集团有限公司 Glass stacking scheduling method
CN112889009A (en) * 2018-10-19 2021-06-01 通快机床两合公司 Method for displaying workpiece representations for assisting a sorting process
CN113814984A (en) * 2021-10-20 2021-12-21 环旭电子股份有限公司 Dynamic image positioning method and system for robot emptying
CN113877854A (en) * 2021-12-08 2022-01-04 辰星(天津)自动化设备有限公司 Object sorting method applied to parallel robot
CN114391126A (en) * 2019-09-16 2022-04-22 Abb瑞士股份有限公司 Method and apparatus for picking and placing items
CN114800484A (en) * 2021-01-28 2022-07-29 精工爱普生株式会社 Robot system control method and robot system
CN114932541A (en) * 2022-06-15 2022-08-23 中迪机器人(盐城)有限公司 Robot-based automatic assembly system and method

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4147930A (en) * 1975-03-20 1979-04-03 U.S. Philips Corporation Object location detector
CN103691678A (en) * 2013-12-10 2014-04-02 殷盛江 Robot for selecting outer diameter sizes of bearings
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
CN103764304A (en) * 2011-04-05 2014-04-30 泽恩机器人有限公司 Method for invalidating sensor measurements after a picking action in a robot system
CN104511436A (en) * 2013-09-28 2015-04-15 沈阳新松机器人自动化股份有限公司 Express sorting method and system based on robot visual servo technology
CN204429717U (en) * 2014-12-18 2015-07-01 河南机电高等专科学校 A kind of bottle cap be applied in bottled drink production equipment detects screening plant
CN105251699A (en) * 2015-11-10 2016-01-20 广东溢达纺织有限公司 Checking and sorting device for sedimentation patches

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4147930A (en) * 1975-03-20 1979-04-03 U.S. Philips Corporation Object location detector
CN103764304A (en) * 2011-04-05 2014-04-30 泽恩机器人有限公司 Method for invalidating sensor measurements after a picking action in a robot system
CN104511436A (en) * 2013-09-28 2015-04-15 沈阳新松机器人自动化股份有限公司 Express sorting method and system based on robot visual servo technology
CN103691678A (en) * 2013-12-10 2014-04-02 殷盛江 Robot for selecting outer diameter sizes of bearings
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
CN204429717U (en) * 2014-12-18 2015-07-01 河南机电高等专科学校 A kind of bottle cap be applied in bottled drink production equipment detects screening plant
CN105251699A (en) * 2015-11-10 2016-01-20 广东溢达纺织有限公司 Checking and sorting device for sedimentation patches

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107597600B (en) * 2017-09-26 2019-08-30 北京京东振世信息技术有限公司 Sorting system and method for sorting
CN107597600A (en) * 2017-09-26 2018-01-19 北京京东尚科信息技术有限公司 Sorting system and method for sorting
CN110371632A (en) * 2018-04-13 2019-10-25 三星显示有限公司 Panel carrying device and panel delivery method
KR20190120463A (en) * 2018-04-13 2019-10-24 삼성디스플레이 주식회사 Apparatus for transferring panel and method for transferring panel
KR102600893B1 (en) * 2018-04-13 2023-11-10 삼성디스플레이 주식회사 Apparatus for transferring panel and method for transferring panel
CN110371632B (en) * 2018-04-13 2023-10-13 三星显示有限公司 Panel conveying device and panel conveying method
CN108993929A (en) * 2018-08-01 2018-12-14 穆科明 A kind of dual-machine linkage industrial machine vision automatic checkout system
CN112889009A (en) * 2018-10-19 2021-06-01 通快机床两合公司 Method for displaying workpiece representations for assisting a sorting process
CN112889009B (en) * 2018-10-19 2024-09-03 通快机床欧洲股份公司 Method and manufacturing system for displaying workpiece illustrations in a manner that assists in sorting processes
CN109352626A (en) * 2018-11-05 2019-02-19 佛山市奇创智能科技有限公司 The equipment and method of robot crawl object
CN109513629A (en) * 2018-11-14 2019-03-26 深圳蓝胖子机器人有限公司 Packages method, apparatus and computer readable storage medium
CN109513630A (en) * 2018-11-14 2019-03-26 深圳蓝胖子机器人有限公司 Packages system and its control method, storage medium
CN109772733A (en) * 2019-01-15 2019-05-21 西安交通大学 A kind of the defect bamboo block detection sorting equipment and method of view-based access control model
CN110294316A (en) * 2019-06-04 2019-10-01 深圳蓝胖子机器人有限公司 Method, system and the equipment of article on a kind of crawl conveyer belt
CN114391126A (en) * 2019-09-16 2022-04-22 Abb瑞士股份有限公司 Method and apparatus for picking and placing items
CN111167731B (en) * 2019-10-23 2022-11-08 武汉库柏特科技有限公司 Product sorting method, product sorting system and intelligent sorting robot
CN111167731A (en) * 2019-10-23 2020-05-19 武汉库柏特科技有限公司 Product sorting method, product sorting system and intelligent sorting robot
CN111112108A (en) * 2019-12-30 2020-05-08 上海交通大学 Hull plate cutting part sorting equipment and method
CN111283685A (en) * 2020-03-05 2020-06-16 广州市斯睿特智能科技有限公司 Vision teaching method of robot based on vision system
CN112024426A (en) * 2020-09-01 2020-12-04 北京智通云联科技有限公司 Multi-station visual identification system
CN112623759A (en) * 2020-12-18 2021-04-09 中国建材国际工程集团有限公司 Glass stacking scheduling method
CN112623759B (en) * 2020-12-18 2023-03-10 中国建材国际工程集团有限公司 Glass stacking scheduling method
CN114800484A (en) * 2021-01-28 2022-07-29 精工爱普生株式会社 Robot system control method and robot system
CN114800484B (en) * 2021-01-28 2023-06-02 精工爱普生株式会社 Control method of robot system and robot system
CN113814984A (en) * 2021-10-20 2021-12-21 环旭电子股份有限公司 Dynamic image positioning method and system for robot emptying
CN113877854A (en) * 2021-12-08 2022-01-04 辰星(天津)自动化设备有限公司 Object sorting method applied to parallel robot
CN114932541A (en) * 2022-06-15 2022-08-23 中迪机器人(盐城)有限公司 Robot-based automatic assembly system and method
CN114932541B (en) * 2022-06-15 2023-07-25 中迪机器人(盐城)有限公司 Robot-based automatic assembly system and method

Also Published As

Publication number Publication date
CN107150032B (en) 2020-06-23

Similar Documents

Publication Publication Date Title
CN107150032A (en) A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method
CN109230580B (en) Unstacking robot system and unstacking robot method based on mixed material information acquisition
CN110509281B (en) Binocular vision-based pose recognition and grabbing device and method
US11046530B2 (en) Article transfer apparatus, robot system, and article transfer method
CN111452040B (en) System and method for associating machine vision coordinate space in a pilot assembly environment
US9990685B2 (en) Automated guidance system and method for a coordinated movement machine
EP2543483B1 (en) Information processing apparatus and information processing method
CN108182689B (en) Three-dimensional identification and positioning method for plate-shaped workpiece applied to robot carrying and polishing field
CN106272424A (en) A kind of industrial robot grasping means based on monocular camera and three-dimensional force sensor
US9233469B2 (en) Robotic system with 3D box location functionality
CN104786226A (en) Posture and moving track positioning system and method of robot grabbing online workpiece
US10377581B2 (en) Article conveying device using at least one sensor
CN204585232U (en) Capture robot pose and the movement locus navigation system of online workpiece
CN110335310B (en) Calibration method under non-common vision field
JP7454132B2 (en) Robot system control device, robot system control method, computer control program, and robot system
US20240003675A1 (en) Measurement system, measurement device, measurement method, and measurement program
CN113793383A (en) 3D visual identification taking and placing system and method
CN111062989B (en) Method and system for calibrating high-precision two-dimensional camera and robot hand and eye
Fan et al. An automatic robot unstacking system based on binocular stereo vision
CN204868885U (en) A robot system for controlling work piece
AU2023244486A1 (en) Controlling a robotic manipulator for packing an object
WO2021256437A1 (en) Imaging device for acquiring three-dimensional information of workpiece surface and two-dimensional image of workpiece
JP7093881B1 (en) System and automatic guided vehicle
Heyer et al. Camera Calibration for Reliable Object Manipulation in Care-Providing Robot FRIEND
CN114901441A (en) Robot system control device, robot system control method, computer control program, and robot system

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