CN105082158A - System and method for grabbing and placing compressor based on image recognition - Google Patents
System and method for grabbing and placing compressor based on image recognition Download PDFInfo
- Publication number
- CN105082158A CN105082158A CN201510437176.8A CN201510437176A CN105082158A CN 105082158 A CN105082158 A CN 105082158A CN 201510437176 A CN201510437176 A CN 201510437176A CN 105082158 A CN105082158 A CN 105082158A
- Authority
- CN
- China
- Prior art keywords
- compressor
- axis
- camera
- pallet
- identification module
- 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
Landscapes
- Image Analysis (AREA)
- Manipulator (AREA)
Abstract
The invention relates to a system and method for grabbing and placing a compressor based on image recognition and belongs to the robot technical field. The devices the system and method relate to comprise an X axis movement system, a Y axis movement system and a Z axis movement system arranged on a support frame and a manipulator arranged at the bottom of a vertical beam in the direction of a Z axis. One side of the manipulator is provided with a first camera. A second camera is arranged on a tray used for placing the compressor. The method for grabbing and placing mainly comprises the following steps that firstly, a photograph of the tray is taken, and the center coordinates of a tray placing point and the angle of the tray are obtained through calculation; then, a photograph of the compressor is taken to obtain the position of the compressor, the compressor is grabbed according to the obtained position, a photograph of the bottom of the compressor is taken, and the final placing position is worked out; and finally, the manipulator places the compressor in a target position accurately. According to the system and method for grabbing and placing the compressor based on image recognition, intelligent grabbing and placing can be conducted; the labor amount is reduced, and meanwhile, the work efficiency is improved.
Description
Technical field
The invention belongs to robotics, be specifically related to the system and method capturing and place compressor, especially based on the crawl of image recognition and the system and method for placement compressor.
Background technology
In industrial production environment, utilizing gripper of manipulator to get to be placed on the workpiece on workbench or conveyer belt, has been sorting or the basic operation of fittage.In air-conditioning production line, compressor on workbench is captured, and compressor is assembled on the pallet of carrying compressor, if this operation adopts artificial realization, not only labour intensity is large, post mobility of people is strong, and work quality can not ensure, there will be the situation damaging compressor to occur, the standardization of work can be accomplished when adopting programme-control machine people to carry out capturing and placing, but this Measures compare sequencing, can not adjust according to actual conditions, need artificial supervision, there will be sky to grab and vacant phenomenon, and when occurring capturing or placing information change, need to change program, this just have impact on carrying out smoothly of production procedure, affect operating efficiency, therefore, be badly in need of one to make corresponding adjustment according to actual conditions thus realize accurately capturing and placing.
Summary of the invention
Method in the present invention employs collected by camera compressor position and the angular image information of two same model, and by the location identification module in compressor home position and the location identification module of compressor drop target image information processed and capture compressor, then calculate capture compressor home position, place the target location of compressor and RA, for industrial improved efficiency and alleviate in hand labor intensity significant.
Concrete technical scheme of the present invention is:
Based on crawl and the system of placing compressor of image recognition, for capturing compressor and being positioned over pallet, system comprises control unit module, by the manipulator that driving mechanism drives, key point is, the first camera for taking compressor home position and target placement location is provided with in this system, described control unit module comprises CPU, the location identification module in the compressor home position of Signal transmissions and the location identification module of compressor drop target is carried out with CPU, the transmitting terminal of the image information of first camera is connected with the signal receiving end of the location identification module in compressor home position and the location identification module of compressor drop target respectively, the location identification module in compressor home position is connected with CPU with the signal output part of the location identification module of compressor drop target, the control signal output of CPU is connected with the drive end of driving mechanism.
Also be provided with the second camera for taking compressor angle in the system of described crawl and placement compressor, the transmitting terminal of the image information of second camera is connected with the signal receiving end of the location identification module of compressor drop target.
Described driving mechanism is the X-axis be arranged on bracing frame, Y-axis, the four-axle linked kinematic system that Z axis linear motion system and Z axis rotary system are formed, X-axis linear motion system comprises the parallel X-axis guide rail being arranged on bracing frame upper end, X-axis guide rail is the Timing Belt around the axis of rolling, X-axis guide rail upper end is fixed with crossbeam, axis of rolling one end is connected with X-axis motor and X-axis decelerator, the Y-axis leading screw along crossbeam direction is provided with in crossbeam, crossbeam side is provided with Z axis holder, Z axis holder is provided with Y-axis swivel nut and matches with Y-axis leading screw, Y-axis leading screw carries out rotary actuation by the y-axis motor and Y-axis decelerator being arranged on crossbeam one end, Z axis holder opposite side is provided with the Z axis guide block swivel nut and vertical beam that are slidably matched, Z axis leading screw is provided with and Z axis swivel nut is slidably matched in vertical beam, vertical beam upper end is provided with Z axis motor and Z axis decelerator drives Z axis screw turns, Z axis motor upper end is connected with brake, manipulator is connected to the lower end of vertical beam by Z axis motor and Z axis decelerator.
Described first camera and second camera are the camera of same model.
Described first camera is fixed on the lower end of vertical beam, and described second camera is fixed on pallet side.
Capture based on compressor and place the system method of carrying out compressor crawl and placement comprise the following steps:
Step S1: first camera is taken pallet image and image information is sent to the location identification module of compressor drop target, the location identification module of compressor drop target obtains the coordinate at leg-of-mutton center and the angle of pallet of three set-point compositions in pallet by image information;
Step S2: first camera takes the compressor map picture location identification module image information being sent to compressor home position that are positioned at home position, the location identification module in compressor home position obtains the original position-information of compressor by image information and is sent to CPU, and then CPU control driving mechanism is got compressor by gripper of manipulator and is delivered to above pallet;
Step S3: second camera is taken compressor ground plan picture and is sent to the location identification module of compressor drop target, the location identification module of compressor drop target obtains the angle information of compressor according to footprint image information and is sent to CPU, CPU is rotated compressor by manipulator according to the pallet Angle ambiguity driving mechanism obtained in step S1, make compressor angle identical with pallet angle, and the final placement location of compressor is calculated according to three dot center's coordinates of pallet that triangle center coordinate and the step S1 of compressor bottom mounting apertures composition obtain.
Compressor is placed on the final placement location that step S3 obtains by step S4:CPU control driving mechanism.
In described step S1, the location identification module acquisition tray position of compressor drop target and the step of angle information comprise:
Step S11:CPU controls driving mechanism and moves to above pallet by first camera, shooting pallet image;
Step S12: pallet image is carried out gradation conversion and generate gray level image, gradation conversion method formula is that gray=1*R+0*G+0*B, gray represent gray level image, and R, G, B represent the brightness of red, green, blue three coloured light respectively;
Step S13: template matches (process of template matches) is carried out to gray level image, finds the approximate location of three protruding set-points, the certain limit limited around each set-point is effective coverage;
Step S14: respectively binaryzation is carried out in three effective coverages, and by binary morphology process, obtain the center position of each protruding set-point;
Step S15: connect three central points and obtain triangle, calculates leg-of-mutton center point coordinate and larger 2 lines of 3 middle x coordinates and horizontal angle;
Step S16: the distance calculating triangle center point coordinates and picture centre, and be transformed into (disX0, disY0) in world coordinate system;
Step S17: according to manipulator present co-ordinate position (xp1, yp1), and the distance obtained in step S16, calculate the coordinate (x1 of manipulator during triangle center and the first camera center superposition of 3 compositions on pallet, y1), formula is: x1=xp1+disX0, y1=yp1+disY0.
The step that the location identification module in described compressor home position obtains compressor home position comprises:
Step S21: first camera is moved to above compressor, shooting compressor photo;
Step S22: compressor photo is carried out gradation conversion and generate gray level image, gradation conversion method formula is that gray=1*R+0*G+0*B, gray represent gray level image, and R, G, B represent the brightness of red, green, blue three coloured light respectively;
Step S23: template matches (details of template and coupling thereof) is carried out to gray level image, finds matched position;
Step S24: the distance calculating matched position and picture centre, and be transformed into world coordinate system (disX1, disY1);
Step S25: the distance (disX2, disY2) calculating first camera and manipulator center;
Step S26: according to Current mechanical hand position coordinate (xp4, yp4), the distance (disX1 of step S24 calculating, disY1) distance (disX2 at first camera and manipulator center and in step S25, disY2), obtain the accurate location (x, y) of compressor, formula is: x=xp4+disX1+disX2, y=yp4+disY1+disY2, CPU control driving mechanism mobile manipulator to carry out compressor crawl and moves to above pallet.
In described step S3, the location identification module acquisition compressor angle of compressor drop target and the step of final placement location comprise:
Step S31: picture centre first camera being moved to the shooting of second camera, note robot coordinate (x2, y2) now;
Step S32: the compressor grabbed is moved to above second camera, shooting compressor bottom panels;
Step S33: compressor bottom image is carried out gradation conversion and generate gray level image, gradation conversion method formula is that gray=1*R+0*G+0*B, gray represent gray level image, and R, G, B represent the brightness of red, green, blue three coloured light respectively;
Step S34: carry out template matches to gray level image, finds three installing holes;
Step S35: according to the position of template matches, the border in location and installation hole, determines the center of circle and the radius of more accurate installing hole by least square method;
Step S36: calculate the larger line of 2 of 3 middle x coordinates and horizontal line angle, the pallet angle according to obtaining in this angle and step S1 rotates, and makes to rotate latter two angle identical;
Step S37: use the method in step S35 to recalculate the center of circle of three installing holes to postrotational image, connect three centers of circle and obtain triangle, calculate three dot center's coordinate positions, and calculate the distance of this position and picture centre, be transformed into world coordinate system;
Step S38: according to manipulator present co-ordinate position (xp0, and the distance (disX3 obtained in step S37 yp0), disY3), coordinate (x3 when calculating triangle center and the second camera center superposition of compressor bottom surface three installing hole composition, y3), formula is: x3=xp0+disX3, y3=yp0+disY3;
Step S39: according to the coordinate (x1 obtained in step S18, y1), robot coordinate (the x2 recorded in step S31, y2) coordinates computed (x3 and in step S38, y3), the final placement location (finalX, finalY) of compressor is calculated, formula is: finalX=x1+ (x2-x3), finalY=y1+ (y2-y3).
The image collected in described step S1, step S2, step S3 is 24 true color images.
The invention has the beneficial effects as follows: the present invention is mainly concerned with in air-conditioning production line, compressor on production line is captured and compressor is placed on the pallet of carrying compressor, first camera and the second camera of shooting image are same model, avoid the difference of the collection image that different model camera causes to the full extent, the location identification module in compressor home position and the location identification module of compressor drop target carry out the process of image information, obtain out the home position of compressor and place position and the angle of compressor, the position that can capture according to actual conditions adjustment and place and angle, supervise without the need to manual site, avoid sky and grab and grab wrong situation generation, ensure that the stable smoothly of work carries out, and flow of personnel will be caused to affect the situation of the progress of work because labour intensity is large, equipment once drops into, Long-Time Service, compare long-term input artificial in a large number, cost obviously reduces, system and method in the present invention is for industrial improved efficiency and alleviate in hand labor intensity significant.
Accompanying drawing explanation
Fig. 1 is the structural representation of the device capturing and place compressor in the present invention.
In accompanying drawing, 1, brake, 2, Z axis motor, 3, Z axis decelerator, 4, vertical beam, 5, crossbeam, 6, manipulator, 7, light fixture, 8, first camera, 9, bracing frame, 10, y-axis motor, 11, Y-axis decelerator, 12, the axis of rolling, 13, X-axis guide rail, 14, X-axis motor, 15, pallet, 16, second camera.
Detailed description of the invention
The present invention relates to the crawl based on image recognition and the system and method placing compressor, based on image recognition crawl with place the system of compressor for capturing compressor and being positioned over pallet 15, system comprises control unit module, by the manipulator 6 that driving mechanism drives, the first camera 8 for taking compressor home position and target placement location is provided with in this system, described control unit module comprises CPU, the location identification module in the compressor home position of Signal transmissions and the location identification module of compressor drop target is carried out with CPU, the transmitting terminal of the image information of first camera 8 is connected with the signal receiving end of the location identification module in compressor home position and the location identification module of compressor drop target respectively, the location identification module in compressor home position is connected with CPU with the signal output part of the location identification module of compressor drop target, the control signal output of CPU is connected with the drive end of driving mechanism, the second camera (16) for taking compressor angle is also provided with in the system of described crawl and placement compressor, the transmitting terminal of the image information of second camera (16) is connected with the signal receiving end of the location identification module of compressor drop target.
Specific embodiment, as shown in Figure 1, described driving mechanism is be arranged on the X-axis on bracing frame 9, Y-axis, the four-axle linked kinematic system that Z axis linear motion system and Z axis rotary system are formed, X-axis linear motion system comprises the parallel X-axis guide rail 13 being arranged on bracing frame 9 upper end, X-axis guide rail 13 is the Timing Belt around the axis of rolling 12, X-axis guide rail 13 upper end is fixed with crossbeam 5, the axis of rolling 12 one end is connected with X-axis motor 14 and X-axis decelerator, the Y-axis leading screw along crossbeam 5 direction is provided with in crossbeam 5, crossbeam 5 side is provided with Z axis holder, Z axis holder is provided with Y-axis swivel nut and matches with Y-axis leading screw, Y-axis leading screw carries out rotary actuation by the y-axis motor 10 and Y-axis decelerator 11 being arranged on crossbeam 5 one end, Z axis holder opposite side is provided with the Z axis swivel nut and vertical beam 4 that are slidably matched, Z axis leading screw is provided with and Z axis swivel nut is slidably matched in vertical beam 4, vertical beam 4 upper end is provided with Z axis motor 2 and Z axis decelerator 3 drives Z axis screw turns, Z axis motor 2 upper end is connected with brake 1, manipulator 6 is connected to the lower end of vertical beam 4 by Z axis motor 2 and Z axis decelerator 3, described first camera 8 and second camera 16 are the camera of same model, first camera 8 is fixed on the lower end of vertical beam 4, second camera 16 is fixed on pallet 15 side.
The method that utilization carries out capturing and placing compressor based on the crawl of said structure and the system of placement compressor comprises the following steps:
Step S1:CPU controls driving mechanism and moves to above pallet 15 by first camera 8, image information is also sent to the location identification module of compressor drop target by shooting pallet 15 image, pallet 15 image is carried out gradation conversion and generates gray level image by the location identification module of compressor drop target, gradation conversion method formula is gray=1*R+0*G+0*B, gray represents gray level image, R, G, B represents red respectively, green, the brightness of blue three color light, template matches is carried out to gray level image, find the approximate location of three protruding set-points, the certain limit limited around each set-point is effective coverage, respectively binaryzation is carried out in three effective coverages, and by binary morphology process, obtain the center position of each protruding set-point, connect three central points and obtain triangle, calculate leg-of-mutton center point coordinate and larger 2 lines of 3 middle x coordinates and horizontal angle, calculate the distance of triangle center point coordinates and picture centre, and be transformed into (disX0 in world coordinate system, disY0), according to manipulator 6 present co-ordinate position (xp1, and (disX0 yp1), disY0), calculate the coordinate (x1 of manipulator 6 during triangle center and first camera 8 center superposition of 3 compositions on pallet 15, y1), formula is: x1=xp1+disX0, y1=yp1+disY0, the location identification module of compressor drop target obtains the coordinate at leg-of-mutton center of three set-point compositions in pallet 15 and the angle of pallet 15 by image information and is sent in CPU,
Step S2: first camera 8 is moved to above compressor, shooting compressor photo, compressor photo is carried out gradation conversion and generate gray level image, gradation conversion method formula is gray=1*R+0*G+0*B, gray represents gray level image, R, G, B represents red respectively, green, the brightness of blue three color light, template matches is carried out to gray level image, find matched position, calculate the distance of matched position and picture centre, and be transformed into world coordinate system (disX1, disY1), calculate the distance (disX2 at first camera 8 and manipulator 6 center, disY2), according to Current mechanical hand 6 position coordinates (xp4, yp4), (disX1, and (disX2 disY1), disY2), obtain the accurate location (x of compressor, y), formula is: x=xp4+disX1+disX2, y=yp4+disY1+disY2, CPU controls driving mechanism mobile manipulator 6 to carry out compressor crawl and moves to above pallet, the location identification module in compressor home position obtains the original position-information of compressor by image information and is sent to CPU, then CPU control driving mechanism captures compressor by manipulator (6) and is delivered to pallet (15) top,
Step S3: picture centre first camera 8 being moved to the shooting of second camera 16, note manipulator 6 coordinate (x2 now, y2), the compressor grabbed is moved to above second camera 16, image information is also sent to the location identification module of compressor drop target by shooting compressor bottom diagram picture, compressor bottom diagram picture is carried out gradation conversion and generates gray level image by location identification module, gradation conversion method formula is gray=1*R+0*G+0*B, gray represents gray level image, R, G, B represents red respectively, green, the brightness of blue three color light, template matches is carried out to gray level image, find three installing holes, according to the position of template matches, the border in location and installation hole, the center of circle and the radius of more accurate installing hole is determined by least square method, calculate the larger line of 2 of 3 middle x coordinates and horizontal line angle, pallet 15 angle according to obtaining in this angle and step S1 rotates, make to rotate latter two angle identical, postrotational image is recalculated to the center of circle of three installing holes, connect three centers of circle and obtain triangle, calculate three dot center's coordinate positions, and calculate the distance of this position and picture centre, be transformed into world coordinate system, according to manipulator 6 present co-ordinate position (xp0, and (disX3 yp0), disY3), coordinate (x3 when calculating triangle center and the second camera center superposition of compressor bottom surface three installing hole composition, y3), formula is: x3=xp0+disX3, y3=yp0+disY3, according to the coordinate (x1 obtained in step S1, y1), manipulator 6 coordinate (x2, and coordinate (x3 y2), y3), calculate the final placement location (finalX of compressor, finalY), formula is: finalX=x1+ (x2-x3), finalY=y1+ (y2-y3), the location identification module of compressor drop target obtains the angle information of compressor according to footprint image information and is sent to CPU, CPU is rotated by manipulator 6 pairs of compressors according to the pallet 15 Angle ambiguity driving mechanism obtained in step S1, make compressor angle identical with pallet 15 angle, and the final placement location of compressor is calculated according to three dot center's coordinates of pallet 15 that triangle center coordinate and the step S1 of compressor bottom mounting apertures composition obtain.
Compressor is placed on the final placement location that step S3 obtains by step S4:CPU control driving mechanism.
The image collected in described step S1, step S2, step S3 is 24 true color images.
Existing crawl and the laying method of stylizing is improved to crawl based on image recognition and laying method by the present invention, the method realizes by based on the crawl of image recognition and the device of placement compressor, this device can the position of autonomous classification compressor and drop target and angle carry out capturing and placing, without the need to manual site's supervision and operation, save a large amount of artificial, device can realize once dropping into Long-Time Service, production cost reduces relatively, and the sky of compressor can be avoided to grab and grab the situation of the subsequent production confusion that mistake causes, can ensure to capture and place work smooth, stable, carry out accurately, for first camera and the second camera use same model of pickup image, can ensure that the similitude of two image shot by cameras is maximum to greatest extent, get rid of the situation that the photo caused because camera is different can not contrast reference.
Claims (10)
1. based on crawl and the system of placing compressor of image recognition, for capturing compressor and being positioned over pallet (15), system comprises control unit module, by the manipulator (6) that driving mechanism drives, it is characterized in that: in this system, be provided with the first camera (8) for taking compressor home position and target placement location, described control unit module comprises CPU, the location identification module in the compressor home position of Signal transmissions and the location identification module of compressor drop target is carried out with CPU, the transmitting terminal of the image information of first camera (8) is connected with the signal receiving end of the location identification module in compressor home position and the location identification module of compressor drop target respectively, the location identification module in compressor home position is connected with CPU with the signal output part of the location identification module of compressor drop target, the control signal output of CPU is connected with the drive end of driving mechanism.
2. the crawl based on image recognition according to claim 1 and the system of placing compressor, it is characterized in that: be also provided with the second camera (16) for taking compressor angle in the system of described crawl and placement compressor, the transmitting terminal of the image information of second camera (16) is connected with the signal receiving end of the location identification module of compressor drop target.
3. the crawl based on image recognition according to claim 2 and the system of placing compressor, it is characterized in that: described driving mechanism is for being arranged on the X-axis on bracing frame (9), Y-axis, the four-axle linked kinematic system that Z axis linear motion system and Z axis rotary system are formed, X-axis linear motion system comprises the parallel X-axis guide rail (13) being arranged on bracing frame (9) upper end, X-axis guide rail (13) is the Timing Belt around the axis of rolling (12), X-axis guide rail (13) upper end is fixed with crossbeam (5), the axis of rolling (12) one end is connected with X-axis motor (14) and X-axis decelerator, the Y-axis leading screw along crossbeam (5) direction is provided with in crossbeam (5), crossbeam (5) side is provided with Z axis holder, Z axis holder is provided with Y-axis swivel nut and matches with Y-axis leading screw, Y-axis leading screw carries out rotary actuation by the y-axis motor (10) and Y-axis decelerator (11) being arranged on crossbeam (5) one end, Z axis holder opposite side is provided with the Z axis swivel nut and vertical beam (4) that are slidably matched, Z axis leading screw is provided with and Z axis swivel nut is slidably matched in vertical beam (4), vertical beam (4) upper end is provided with Z axis motor (2) and Z axis decelerator (3) drives Z axis screw turns, Z axis motor (2) upper end is connected with brake (1), manipulator (6) is connected to the lower end of vertical beam (4) by Z axis motor (2) and Z axis decelerator (3).
4. the crawl based on image recognition according to claim 2 and the system of placing compressor, is characterized in that: the camera that described first camera (8) and second camera (16) are same model.
5. the system of the crawl based on image recognition according to claim 3 and placement compressor, it is characterized in that: described first camera (8) is fixed on the lower end of vertical beam (4), and described second camera (16) is fixed on pallet (15) side.
6. carry out the method for compressor crawl and placement based on system according to claim 2, it is characterized in that, the method that described compressor captures and places comprises the following steps:
Step S1: first camera (8) is taken pallet (15) image and image information is sent to the location identification module of compressor drop target, the location identification module of compressor drop target obtains the coordinate at leg-of-mutton center and the angle of pallet (15) of three set-point compositions in pallet (15) by image information;
Step S2: first camera (8) takes the compressor map picture location identification module image information being sent to compressor home position that are positioned at home position, the location identification module in compressor home position obtains the original position-information of compressor by image information and is sent to CPU, and then CPU control driving mechanism captures compressor by manipulator (6) and is delivered to pallet (15) top;
Step S3: second camera (16) is taken compressor ground plan picture and is sent to the location identification module of compressor drop target, the location identification module of compressor drop target obtains the angle information of compressor according to footprint image information and is sent to CPU, CPU is rotated compressor by manipulator (6) according to the pallet obtained in step S1 (15) Angle ambiguity driving mechanism, make compressor angle identical with pallet (15) angle, and the final placement location of compressor is calculated according to three dot center's coordinates of pallet (15) that triangle center coordinate and the step S1 of compressor bottom mounting apertures composition obtain.
Compressor is placed on the final placement location that step S3 obtains by step S4:CPU control driving mechanism.
7. the method for compressor crawl according to claim 6 and placement, is characterized in that, in described step S1, location identification module acquisition pallet (15) position of compressor drop target and the step of angle information comprise:
Step S11:CPU controls driving mechanism and first camera (8) is moved to pallet (15) top, shooting pallet (15) image;
Step S12: pallet (15) image is carried out gradation conversion and generate gray level image, gradation conversion method formula is that gray=1*R+0*G+0*B, gray represent gray level image, and R, G, B represent the brightness of red, green, blue three coloured light respectively;
Step S13: carry out template matches to gray level image, finds the approximate location of three protruding set-points in pallet (15), and the certain limit limited around each set-point is effective coverage;
Step S14: respectively binaryzation is carried out in three effective coverages, and by binary morphology process, obtain the center position of each protruding set-point;
Step S15: connect three central points and obtain triangle, calculates leg-of-mutton center point coordinate and larger 2 lines of 3 middle x coordinates and horizontal angle;
Step S16: the distance calculating triangle center point coordinates and picture centre, and be transformed into (disX0, disY0) in world coordinate system;
Step S17: according to manipulator (6) present co-ordinate position (xp1, yp1), and the distance obtained in step S16, calculate pallet (15) upper 3 composition triangle center and first camera (8) center superposition time manipulator (6) coordinate (x1, y1), formula is: x1=xp1+disX0, y1=yp1+disY0.
8. the compressor according to claim 6 method that captures and place, is characterized in that, the step that the location identification module in described compressor home position obtains compressor home position comprises:
Step S21: first camera (8) is moved to above compressor, shooting compressor photo;
Step S22: compressor photo is carried out gradation conversion and generate gray level image, gradation conversion method formula is that gray=1*R+0*G+0*B, gray represent gray level image, and R, G, B represent the brightness of red, green, blue three coloured light respectively;
Step S23: template matches is carried out to gray level image, finds matched position;
Step S24: the distance calculating matched position and picture centre, and be transformed into world coordinate system (disX1, disY1);
Step S25: the distance (disX2, disY2) calculating first camera (8) and manipulator (6) center;
Step S26: according to Current mechanical hand (6) position coordinates (xp4, yp4), the distance (disX1 of step S24 calculating, disY1) distance (disX2 at first camera (8) and manipulator (6) center and in step S25, disY2), obtain the accurate location (x of compressor, y), formula is: x=xp4+disX1+disX2, y=yp4+disY1+disY2, CPU control driving mechanism mobile manipulator (6) to carry out compressor crawl and moves to above pallet.
9. the method for compressor crawl according to claim 6 and placement, is characterized in that, in described step S3, the location identification module acquisition compressor angle of compressor drop target and the step of final placement location comprise:
Step S31: picture centre first camera (8) being moved to the shooting of second camera (16), note manipulator (6) coordinate (x2, y2) now;
Step S32: the compressor grabbed is moved to second camera (16) top, shooting compressor bottom panels;
Step S33: compressor bottom image is carried out gradation conversion and generate gray level image, gradation conversion method formula is that gray=1*R+0*G+0*B, gray represent gray level image, and R, G, B represent the brightness of red, green, blue three coloured light respectively;
Step S34: carry out template matches to gray level image, finds three installing holes;
Step S35: according to the position of template matches, the border in location and installation hole, determines the center of circle and the radius of more accurate installing hole by least square method;
Step S36: calculate the larger line of 2 of 3 middle x coordinates and horizontal line angle, rotate according to the pallet obtained in this angle and step S1 (15) angle, make to rotate latter two angle identical;
Step S37: use the method in step S35 to recalculate the center of circle of three installing holes to postrotational image, connect three centers of circle and obtain triangle, calculate three dot center's coordinate positions, and calculate the distance of this position and picture centre, be transformed into world coordinate system;
Step S38: according to manipulator (6) present co-ordinate position (xp0, and the distance (disX3 obtained in step S37 yp0), disY3), coordinate (x3 when calculating triangle center and the second camera center superposition of compressor bottom surface three installing hole composition, y3), formula is: x3=xp0+disX3, y3=yp0+disY3;
Step S39: according to the coordinate (x1 obtained in step S18, y1), manipulator (6) coordinate (x2 recorded in step S31, y2) coordinates computed (x3 and in step S38, y3), the final placement location (finalX, finalY) of compressor is calculated, formula is: finalX=x1+ (x2-x3), finalY=y1+ (y2-y3).
10. the method for compressor crawl according to claim 6 and placement, it is characterized in that, the image collected in described step S1, step S2, step S3 is 24 true color images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510437176.8A CN105082158B (en) | 2015-07-23 | 2015-07-23 | Method for grabbing and placing compressor based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510437176.8A CN105082158B (en) | 2015-07-23 | 2015-07-23 | Method for grabbing and placing compressor based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105082158A true CN105082158A (en) | 2015-11-25 |
| CN105082158B CN105082158B (en) | 2017-01-11 |
Family
ID=54563928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510437176.8A Active CN105082158B (en) | 2015-07-23 | 2015-07-23 | Method for grabbing and placing compressor based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105082158B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106040613A (en) * | 2016-05-24 | 2016-10-26 | 四川研宝科技有限公司 | Automatic power detection method |
| CN106091922A (en) * | 2016-05-25 | 2016-11-09 | 广州市思林杰自动化科技有限公司 | A kind of method and device that workpiece is detected |
| CN106829469A (en) * | 2017-03-30 | 2017-06-13 | 武汉库柏特科技有限公司 | A kind of unordered grabbing device of robot based on double camera and method |
| CN106960099A (en) * | 2017-03-28 | 2017-07-18 | 清华大学 | A kind of manipulator grasp stability recognition methods based on deep learning |
| CN107999330A (en) * | 2017-12-29 | 2018-05-08 | 科睿驰（深圳）医疗科技发展有限公司 | A kind of the automation conduit coating equipment and method of view-based access control model processing |
| CN109968237A (en) * | 2019-03-19 | 2019-07-05 | 珠海格力智能装备有限公司 | Mounting and positioning method and device of air conditioner |
| CN111240329A (en) * | 2020-01-17 | 2020-06-05 | 广东智源机器人科技有限公司 | Intelligent robot control method and device and intelligent robot |
| CN113997290A (en) * | 2021-11-17 | 2022-02-01 | 合肥联宝信息技术有限公司 | Control method and equipment for mechanical arm |
| CN117911372A (en) * | 2024-01-19 | 2024-04-19 | 河北省科学院应用数学研究所 | Furnace frame polishing method and system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109760463A (en) * | 2018-12-29 | 2019-05-17 | 广东博智林机器人有限公司 | Wallpaper piece alignment means and the method for carrying out the alignment of wallpaper seam using it |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1882242A (en) * | 2005-06-02 | 2006-12-20 | 重机公司 | Element mounting device |
| CN101026952A (en) * | 2006-02-16 | 2007-08-29 | 重机公司 | Electronic component mounting method and device |
| CN101187549A (en) * | 2007-12-28 | 2008-05-28 | 谭建平 | Method and device for on-line monitoring multiple movable member center using double laser beam |
| CN101362332A (en) * | 2007-08-09 | 2009-02-11 | 富士通株式会社 | Part-delivery apparatus and method for the same |
| JP2010221381A (en) * | 2009-03-25 | 2010-10-07 | Fuji Xerox Co Ltd | Method for assembling part and device for assembling the part |
| CN204324384U (en) * | 2014-11-21 | 2015-05-13 | 河北科技大学 | Based on object localization and the crawl platform of opto-electronic pickup |
-
2015
- 2015-07-23 CN CN201510437176.8A patent/CN105082158B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1882242A (en) * | 2005-06-02 | 2006-12-20 | 重机公司 | Element mounting device |
| CN101026952A (en) * | 2006-02-16 | 2007-08-29 | 重机公司 | Electronic component mounting method and device |
| CN101362332A (en) * | 2007-08-09 | 2009-02-11 | 富士通株式会社 | Part-delivery apparatus and method for the same |
| CN101187549A (en) * | 2007-12-28 | 2008-05-28 | 谭建平 | Method and device for on-line monitoring multiple movable member center using double laser beam |
| JP2010221381A (en) * | 2009-03-25 | 2010-10-07 | Fuji Xerox Co Ltd | Method for assembling part and device for assembling the part |
| CN204324384U (en) * | 2014-11-21 | 2015-05-13 | 河北科技大学 | Based on object localization and the crawl platform of opto-electronic pickup |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106040613A (en) * | 2016-05-24 | 2016-10-26 | 四川研宝科技有限公司 | Automatic power detection method |
| CN106091922A (en) * | 2016-05-25 | 2016-11-09 | 广州市思林杰自动化科技有限公司 | A kind of method and device that workpiece is detected |
| CN106091922B (en) * | 2016-05-25 | 2019-05-14 | 广州市思林杰自动化科技有限公司 | The method and device that a kind of pair of workpiece is detected |
| CN106960099A (en) * | 2017-03-28 | 2017-07-18 | 清华大学 | A kind of manipulator grasp stability recognition methods based on deep learning |
| CN106960099B (en) * | 2017-03-28 | 2019-07-26 | 清华大学 | A kind of manipulator grasp stability recognition methods based on deep learning |
| CN106829469A (en) * | 2017-03-30 | 2017-06-13 | 武汉库柏特科技有限公司 | A kind of unordered grabbing device of robot based on double camera and method |
| CN107999330A (en) * | 2017-12-29 | 2018-05-08 | 科睿驰（深圳）医疗科技发展有限公司 | A kind of the automation conduit coating equipment and method of view-based access control model processing |
| CN109968237A (en) * | 2019-03-19 | 2019-07-05 | 珠海格力智能装备有限公司 | Mounting and positioning method and device of air conditioner |
| CN109968237B (en) * | 2019-03-19 | 2021-11-23 | 珠海格力智能装备有限公司 | Mounting and positioning method and device of air conditioner |
| CN111240329A (en) * | 2020-01-17 | 2020-06-05 | 广东智源机器人科技有限公司 | Intelligent robot control method and device and intelligent robot |
| CN113997290A (en) * | 2021-11-17 | 2022-02-01 | 合肥联宝信息技术有限公司 | Control method and equipment for mechanical arm |
| CN117911372A (en) * | 2024-01-19 | 2024-04-19 | 河北省科学院应用数学研究所 | Furnace frame polishing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105082158B (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105082158A (en) | System and method for grabbing and placing compressor based on image recognition | |
| CN107414832A (en) | A kind of mobile mechanical arm crawl control system and method based on machine vision | |
| CN109483531B (en) | Machine vision system and method for picking and placing FPC board by manipulator at fixed point | |
| CN207206429U (en) | A kind of mobile mechanical arm crawl control system based on machine vision | |
| CN110605718A (en) | Transformer substation inspection robot system and inspection method | |
| CN110276799B (en) | Coordinate calibration method, calibration system and mechanical arm | |
| CN205238065U (en) | Snatch many sucking discs manipulator of irregularity body | |
| CN109454638A (en) | A kind of robot grasping system of view-based access control model guidance | |
| CN105397831A (en) | Multi-suction-cup manipulator capable of grabbing irregular objects | |
| CN107053188A (en) | A kind of hot line robot branch connects gage lap method | |
| CN104308530A (en) | Vision detection-based isolator star wheel automated assembly device | |
| CN111300405B (en) | Visual identification positioning device and method for mobile platform | |
| CN109954254B (en) | Badminton court intelligence is picked up football robot based on wheel of coming fortune of qxcomm technology | |
| CN104308531A (en) | Vision detection-based isolator star wheel automated assembly method | |
| CN109459984B (en) | Positioning and grabbing system based on three-dimensional point cloud and using method thereof | |
| CN110219446B (en) | Automatic brick paving method | |
| CN110233440B (en) | Become distribution equipment inspection device | |
| CN108174111A (en) | Crusing robot target image grasping means | |
| CN107065852A (en) | A kind of photovoltaic plant inspection operational system and its method | |
| CN111390910A (en) | Manipulator target grabbing and positioning method, computer readable storage medium and manipulator | |
| CN109494617A (en) | One kind is removed obstacles crusing robot and its method of removing obstacles | |
| CN109848986B (en) | Positioning method for uncertain height of target object based on machine vision | |
| CN206728172U (en) | A kind of video monitoring apparatus | |
| CN110212644B (en) | Isolating switch working state monitoring system and method | |
| CN205734926U (en) | A kind of identification automatically based on image procossing and location Bai Qi robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |