CN114359393A - Cross-platform visual guide dispensing guiding method - Google Patents

Cross-platform visual guide dispensing guiding method Download PDF

Info

Publication number
CN114359393A
CN114359393A CN202210262967.1A CN202210262967A CN114359393A CN 114359393 A CN114359393 A CN 114359393A CN 202210262967 A CN202210262967 A CN 202210262967A CN 114359393 A CN114359393 A CN 114359393A
Authority
CN
China
Prior art keywords
image
dispensing
coordinate system
coordinate
axis
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
CN202210262967.1A
Other languages
Chinese (zh)
Other versions
CN114359393B (en
Inventor
曲东升
李长峰
王承峰
郜福亮
陈辉
苗虎
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.)
Changzhou Mingseal Robotic Technology Co Ltd
Original Assignee
Changzhou Mingseal Robotic Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changzhou Mingseal Robotic Technology Co Ltd filed Critical Changzhou Mingseal Robotic Technology Co Ltd
Priority to CN202210262967.1A priority Critical patent/CN114359393B/en
Publication of CN114359393A publication Critical patent/CN114359393A/en
Application granted granted Critical
Publication of CN114359393B publication Critical patent/CN114359393B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Abstract

The invention discloses a cross-platform visual guide dispensing guiding method, which comprises the following steps: step 1, collecting an image; step 2, drawing a characteristic area, and creating a matching positioning template; step 3, teaching a glue path, and generating a visual model of a glue dispensing track; step 4, searching a matching template; 5, transferring the model to an image coordinate system; step 6, transferring the image coordinate system to a mechanical axis coordinate system; 7, calculating absolute mechanical axis coordinates of coordinate points in the dispensing track visual model; and 8, outputting the model coordinate points, and executing coordinate dispensing by the lower computer. The cross-platform visual guide dispensing guiding method has the advantages that the dispensing track visual model and the guiding relocation thereof can be shared among different devices.

Description

Cross-platform visual guide dispensing guiding method
Technical Field
The invention relates to the technical field of visual guide dispensing, in particular to a cross-platform visual guide dispensing guide method.
Background
In order to realize that the industrial camera guides the mechanical shaft to finish accurate dispensing operation, the industrial camera is widely installed on the mechanical shaft to realize 2D visual guide dispensing, and the method comprises the following specific steps: step 1, calibrating the position relation of an industrial camera and a dispensing needle head under a mechanical axis coordinate system; step 2, teaching a dispensing track visual model of the product; and 3, guiding and repositioning the dispensing track visual model of the product.
Aiming at the step 2, the traditional visual model of the dispensing track is composed of a glue path axis coordinate point set and an image coordinate point at the center of a template area. The template area is the interesting area matched with the Halcon template, drawing and creating are carried out in the reference image, and area positioning similar to the interesting area characteristic is searched in other images.
Aiming at the step 3, the guiding repositioning mode of the visual model of the dispensing track of the product is as follows: and (3) performing translation transformation on the shaft position of the real-time product during drawing compared with the shaft position during glue path teaching, matching and positioning the position and the angle of the real-time product by using a template compared with the translation and rotation transformation of the position of the product during glue path teaching, solving an affine matrix of the transformation, and performing affine matrix transformation on a dispensing track visual model to complete the guided repositioning of the dispensing track visual model of the current product. The template matching is a method for positioning an object in an image provided in a Halcon image processing algorithm library, and the main idea is to use a region of interest in a reference image as a template, create the region of interest and search the model in other images.
In actual generation, a product often uses a plurality of devices to operate in parallel, imaging magnifications of cameras among different devices are different, a traditional dispensing track visual model and a guiding method are used on different devices, due to the fact that the imaging magnifications among the devices are not consistent, the imaging position of the dispensing track visual model in an image can be zoomed and transformed by taking the center of the image as an original point, and then a model imaging coordinate is translated towards the center, model translation generated by zooming is not considered in the traditional mode, and finally the guiding repositioning position of a glue path is wrong, so that the same model is used among different devices to guide dispensing to be not communicated.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art.
Therefore, the invention provides a cross-platform visual guide dispensing guiding method, which has the advantage that a dispensing track visual model and a guide repositioning thereof can be shared among different devices.
The cross-platform visual guide dispensing guiding method provided by the embodiment of the invention comprises the following steps: step 1, collecting images: placing the product at the center of the image view, and adjusting parameters of a light source, a camera and a lens until the product image is clear and the contrast is clear; step 2, drawing a characteristic area, and creating a matching positioning template: drawing a characteristic region on a reference image, creating a matching template, and calculating the mechanical axis coordinate of a template central point according to the mechanical axis coordinate of a camera, a camera calibration matrix and the image coordinate of the template central point during reference image acquisition; step 3, teaching a glue path, and generating a visual model of a glue dispensing track: moving a camera shaft, aligning the central point of the image to the top point of the contour to be taught on the glue path, recording the coordinate of the mechanical shaft at the moment, and generating a visual model of the glue dispensing track by combining the coordinate of the mechanical shaft of the central point of the template in the step 2; step 4, searching a matching template: searching a matching template, positioning the image coordinate of the center point of the template, and recording the mechanical axis coordinate when the image is taken currently; and 5, transferring the model to an image coordinate system: combining the dispensing track visual model in the step 3 and the template central point image coordinates in the step 4, calculating a pixel scale according to a current equipment camera calibration matrix, and converting the dispensing track visual model into an image coordinate system; and 6, transferring the image coordinate system to a mechanical axis coordinate system: according to the current equipment camera calibration matrix, the dispensing track visual model is converted from an image coordinate system to a mechanical axis coordinate system, and a target coordinate point of the mechanical axis to be moved is solved; 7, calculating absolute mechanical axis coordinates of coordinate points in the dispensing track visual model; and 8, outputting the model coordinate points, and executing coordinate dispensing by the lower computer: and outputting the target coordinate point calculated in the step 6 to lower computer software to perform dispensing.
The invention has the advantages that the teaching workload of the dispensing track visual model of the similar product is reduced, and the similar product can be shared only by establishing one dispensing track visual model; the consistency of the dispensing process among the devices of the same type of products is improved.
According to one embodiment of the invention, the camera is mounted on a camera axis, the camera moving synchronously with the camera axis.
According to an embodiment of the present invention, in the step 2, an image is obtained according to the step 1, a template region of interest is drawn in the image and used as a template region to create a template, and the current image is the reference image.
According to an embodiment of the present invention, in the step 3, the mechanical axis coordinate system is
Figure 167538DEST_PATH_IMAGE001
And the coordinate system 0 point is established at the original position of the mechanical axis x and y reset points, the directions of the x and y axes are based on the installation direction of the mechanical axis, the directions of the x axis and the y axis are orthogonal, and the dimension of the x axis and the y axis is length.
According to an embodiment of the present invention, in the 5 th step and the 6 th step, the image coordinate system is
Figure 107812DEST_PATH_IMAGE002
And the coordinate system 0 point is established at the upper left corner of the image, the x-axis direction and the y-axis direction are based on the rows and the columns of the image, the x-axis direction and the y-axis direction are orthogonal, and the x-axis and the y-axis are pixels.
According to an embodiment of the present invention, in the step 3, the coordinates of the vertex of the outline of the visual model of the dispensing trajectory are all based on a model coordinate system.
According to one embodiment of the present invention, the model coordinate system is
Figure 631197DEST_PATH_IMAGE002
And establishing a coordinate system 0 point on the central point of the matching template in the step 2, wherein the x-axis direction and the y-axis direction are orthogonal based on the rows and the columns of the image, and the x-axis scale and the y-axis scale are lengths.
According to an embodiment of the present invention, in the 2 nd step, the camera calibration matrix is represented as: image coordinate system during plane motion of mechanical axis
Figure 733145DEST_PATH_IMAGE002
Transferring the moving distance to a mechanical axis coordinate system
Figure 974771DEST_PATH_IMAGE001
And moving the relation matrix between the intervals downwards.
According to an embodiment of the present invention, in the step 3, the calculation steps of the coordinates of each vertex model on the outline of the visual model of the dispensing trajectory are as follows:
first, the
Figure 453156DEST_PATH_IMAGE003
Calculating the displacement of each vertex of the contour of the rubber road relative to the coordinate of the mechanical axis of the camera when the reference image is collected;
first, the
Figure 768731DEST_PATH_IMAGE004
Step (A) to
Figure 307160DEST_PATH_IMAGE003
Transferring the displacement obtained by calculation in the step to an image coordinate system to obtain a converted point;
first, the
Figure 770502DEST_PATH_IMAGE005
Step (A) to
Figure 114896DEST_PATH_IMAGE004
And transferring the converted points obtained in the step to a model coordinate system, and finally obtaining each vertex model coordinate on the outline of the visual model of the dispensing track.
According to an embodiment of the present invention, in the 4 th step, the 5 th step, the 6 th step, the 7 th step and the 8 th step, the guiding relocation of the established visual model of the dispensing trajectory can be used among different devices of the same type.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic view of a machine axis coordinate system;
FIG. 3 is a schematic diagram of an image coordinate system and a model coordinate system.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The cross-platform visual guidance dispensing guiding method according to the embodiment of the invention is described in detail below with reference to the accompanying drawings.
Referring to fig. 1, the cross-platform visual guidance dispensing guiding method of the present invention mainly includes creating a dispensing trajectory visual model capable of sharing parameters and a guidance relocation of the dispensing trajectory visual model capable of sharing parameters, so as to solve the problem that the dispensing trajectory visual model and the guidance relocation thereof cannot be shared among different devices, and specifically includes the following steps:
step 1, collecting images: and (4) placing the product to about the center of the image view, and adjusting parameters of a light source, a camera and a lens until the product image is clear and the contrast is clear. Wherein the camera is mounted on a camera axis, the camera moving synchronously with the camera axis.
Step 2, drawing a characteristic area, and creating a matching positioning template: drawing characteristic regions on the reference image, creating a matching template, and acquiring the coordinates of the mechanical axis of the camera according to the reference image
Figure 550557DEST_PATH_IMAGE006
Camera calibration matrix
Figure 56624DEST_PATH_IMAGE007
Template center point image coordinates
Figure 210525DEST_PATH_IMAGE008
And calculating the mechanical axis coordinate of the center point of the template
Figure 93030DEST_PATH_IMAGE009
Center point of template mechanical axis coordinate
Figure 320881DEST_PATH_IMAGE010
The calculation formula of (a) is as follows:
Figure 997850DEST_PATH_IMAGE011
(1)
in formula (1), the meaning of each symbol is specifically as follows:
Figure 373467DEST_PATH_IMAGE012
representing the coordinates of the mechanical axis of the center point of the template, and
Figure 59664DEST_PATH_IMAGE013
Figure 204337DEST_PATH_IMAGE006
representing the coordinates of the mechanical axis of the camera at the time of reference image acquisition, and
Figure 317787DEST_PATH_IMAGE014
Figure 243017DEST_PATH_IMAGE015
representing a scaling matrix;
Figure 405008DEST_PATH_IMAGE016
representing a rotation matrix;
Figure 732084DEST_PATH_IMAGE017
representing a camera calibration matrix;
Figure 954118DEST_PATH_IMAGE008
expressed as matched template center point image coordinates, and
Figure 101066DEST_PATH_IMAGE018
Figure 66748DEST_PATH_IMAGE019
expressed as image coordinates of the center point of the image, and
Figure 248331DEST_PATH_IMAGE020
the image coordinates represent point coordinates in an image coordinate system. The mechanical axis coordinates represent point coordinates in the mechanical axis coordinate system.
In the step 2, an image is obtained according to the step 1, a template region of interest is drawn in the image and is used as a template region to create a template, and the current image is a reference image.
In step 2, the camera calibration matrix is represented as: image coordinate system during plane motion of mechanical axis
Figure 641266DEST_PATH_IMAGE002
Transferring the moving distance to a mechanical axis coordinate system
Figure 541089DEST_PATH_IMAGE001
And moving the relation matrix between the intervals downwards. The transformation relation is as follows: firstly, rotating transformation and then scaling transformation:
Figure 44882DEST_PATH_IMAGE021
(2)
in formula (2), the meaning of each symbol is specifically as follows:
Figure 80971DEST_PATH_IMAGE022
to represent
Figure 656527DEST_PATH_IMAGE023
A movement pitch of the direction;
Figure 778066DEST_PATH_IMAGE024
to represent
Figure 147868DEST_PATH_IMAGE025
A movement pitch of the direction;
Figure 241726DEST_PATH_IMAGE026
to represent
Figure 976464DEST_PATH_IMAGE027
Is axially arranged at
Figure 585300DEST_PATH_IMAGE023
Scale factors on the axis;
Figure 493213DEST_PATH_IMAGE028
to represent
Figure 441577DEST_PATH_IMAGE029
Is axially arranged at
Figure 409533DEST_PATH_IMAGE025
Scale factors on the axis;
Figure 443348DEST_PATH_IMAGE030
to represent
Figure 154952DEST_PATH_IMAGE031
A movement pitch in a direction;
Figure 223402DEST_PATH_IMAGE032
to represent
Figure 362260DEST_PATH_IMAGE029
A movement pitch in a direction;
Figure 617792DEST_PATH_IMAGE033
indicates the angle of rotation;
Figure 70770DEST_PATH_IMAGE015
representing a scaling matrix
Figure 56043DEST_PATH_IMAGE034
Figure 303485DEST_PATH_IMAGE016
Representing a rotation matrix
Figure 108630DEST_PATH_IMAGE035
Step 3, demonstrating the glue path, generating glue dispensing railsA handwriting vision model: moving a camera shaft, aligning the central point of an image to the top point of a contour to be taught on a glue line, recording the coordinates of a mechanical shaft at the moment, and inserting all recorded mechanical shaft coordinates into the array after teaching is finished
Figure 99720DEST_PATH_IMAGE036
In (1),
Figure 939500DEST_PATH_IMAGE037
wherein the length of the array is i,
Figure 420160DEST_PATH_IMAGE038
and the coordinates of each vertex mechanical axis on the outline of the visual model of the dispensing track are represented. Combining the template center point mechanical axis coordinates of step 2
Figure 915863DEST_PATH_IMAGE009
And generating a visual model of the dispensing track.
In step 3, see FIG. 2, the machine axis coordinate system is
Figure 445065DEST_PATH_IMAGE001
The coordinate system 0 point is established at a mechanical axis x and y reset original point, the x and y axis directions are based on the installation direction of a mechanical axis, the x axis direction is orthogonal to the y axis direction, the x and y axis dimensions are lengths, and the length unit is mm; the symbol a is used to distinguish different coordinate systems and a is the first letter of axis (coordinate axes).
Referring to fig. 3, in step 3, the coordinates of the vertex of the outline of the visual model of the dispensing trajectory are all based on the model coordinate system. System of coordinates of model
Figure 404930DEST_PATH_IMAGE039
Establishing a coordinate system 0 point on the central point of the matching template in the step 2, wherein the x-axis direction and the y-axis direction are orthogonal based on the rows and the columns of the image, the x-axis direction and the y-axis direction are length, and the unit of the length is mm; the notation t is used to distinguish different coordinate systems and t is the first letter of the template.
It should be noted that the trace vision is glued to the pointModel array
Figure 994175DEST_PATH_IMAGE040
The components of the composition are as follows,
Figure 711595DEST_PATH_IMAGE041
has a length of
Figure 106804DEST_PATH_IMAGE042
Figure 858859DEST_PATH_IMAGE043
And representing the coordinates of each vertex model on the outline of the visual model of the dispensing track.
In step 3, dispensing each vertex model coordinate on the visual model contour of the track
Figure 681322DEST_PATH_IMAGE043
The calculation steps are as follows:
first, the
Figure 948355DEST_PATH_IMAGE003
Step, calculating each vertex of the contour of the rubber road
Figure 960305DEST_PATH_IMAGE044
Mechanical axis coordinates of camera during relative reference image acquisition
Figure 629183DEST_PATH_IMAGE006
A displacement of
Figure 560230DEST_PATH_IMAGE042
The relative displacement of each vertex is marked as
Figure 314560DEST_PATH_IMAGE045
Then, the displacement calculation formula is as follows:
Figure 317151DEST_PATH_IMAGE046
(3)
first, the
Figure 778219DEST_PATH_IMAGE047
Step (A) to
Figure 942484DEST_PATH_IMAGE003
Displacement calculated in step(s)
Figure 121793DEST_PATH_IMAGE045
Transferring to image coordinate system to obtain converted points, and recording the converted points as
Figure 662496DEST_PATH_IMAGE048
Then point after conversion
Figure 853437DEST_PATH_IMAGE049
The calculation formula of (a) is as follows:
Figure 454182DEST_PATH_IMAGE050
(4)
in formula (4), the meaning of each symbol is specifically as follows:
Figure 855208DEST_PATH_IMAGE051
representing the inverse of the camera calibration matrix.
First, the
Figure 199601DEST_PATH_IMAGE052
Step (A) to
Figure 369683DEST_PATH_IMAGE047
Converted points obtained in step(s)
Figure 141330DEST_PATH_IMAGE049
Go to the model coordinate system
Figure 29651DEST_PATH_IMAGE053
Finally obtaining the coordinates of each vertex model on the outline of the visual model of the dispensing track
Figure 912157DEST_PATH_IMAGE054
Then, then
Figure 202324DEST_PATH_IMAGE055
The calculation formula of (a) is as follows:
Figure 144872DEST_PATH_IMAGE056
(5)
in formula (5), the meaning of each symbol is specifically as follows:
Figure 520490DEST_PATH_IMAGE057
representing a scaling matrix;
Figure 206686DEST_PATH_IMAGE058
representing the converted points.
Step 4, searching a matching template: searching for matching template to locate template center point image coordinates
Figure 351359DEST_PATH_IMAGE059
And recording the mechanical axis coordinates at that time
Figure 464809DEST_PATH_IMAGE060
And 5, transferring the model to an image coordinate system: combining the dispensing track visual model in the step 3 and the template central point image coordinates in the step 4, and calibrating the matrix according to the current equipment camera
Figure 327723DEST_PATH_IMAGE061
And calculating pixel scale, and converting the dispensing track visual model into an image coordinate system.
In step 5, the current device camera calibration matrix is recorded
Figure 552031DEST_PATH_IMAGE061
Wherein, in the step (A),
Figure 680437DEST_PATH_IMAGE061
a matrix representing a particular device camera, referred to herein as the current device camera.
In step 4, the template center point image coordinates are marked
Figure 699209DEST_PATH_IMAGE059
Calculating a rotation matrix from the rotation angle of the template, the rotation matrix being written as
Figure 111736DEST_PATH_IMAGE062
Visual model of created dispensing trajectory
Figure 77418DEST_PATH_IMAGE063
Recording the image dispensing track visual model under the current image coordinate system of the current equipment
Figure 196683DEST_PATH_IMAGE064
In which the point coordinates
Figure 651935DEST_PATH_IMAGE065
The calculation formula of (a) is as follows:
Figure 223862DEST_PATH_IMAGE066
(6)
in the formula (6), the meaning of each symbol is specifically as follows:
Figure 789973DEST_PATH_IMAGE067
representing a current device camera scaling matrix;
Figure 29324DEST_PATH_IMAGE062
a rotation matrix representing a rotation angle of the template;
Figure 593161DEST_PATH_IMAGE068
represents the ith element in the array, an
Figure 714701DEST_PATH_IMAGE042
Is a positive integer of 1 or more.
It should be noted that, in the following description,
Figure 22185DEST_PATH_IMAGE069
and the image dispensing track visual model represents a current image coordinate system.
Figure 178360DEST_PATH_IMAGE070
And point coordinates in the image dispensing track visual model under the current image coordinate system are represented.
And 6, transferring the image coordinate system to a mechanical axis coordinate system: calibrating a matrix according to a current device camera
Figure 913098DEST_PATH_IMAGE061
And (4) transferring the dispensing track visual model from the image coordinate system to the mechanical axis coordinate system, and solving a target coordinate point to be moved by the mechanical axis. Specifically, the 5 th step
Figure 521934DEST_PATH_IMAGE064
Axial point gluing track visual model under current equipment mechanical axis coordinate system
Figure 367530DEST_PATH_IMAGE071
In which the point coordinates
Figure 378211DEST_PATH_IMAGE072
The calculation formula of (a) is as follows:
Figure 283850DEST_PATH_IMAGE073
(7)
in formula (7), the meaning of each symbol is specifically as follows:
Figure 379982DEST_PATH_IMAGE074
represents the ith element in the array, an
Figure 91586DEST_PATH_IMAGE042
Is a positive integer of 1 or more.
It should be noted that, in the following description,
Figure 894457DEST_PATH_IMAGE075
and representing a visual model of the axis point gluing track under the current mechanical axis coordinate system.
Figure 33315DEST_PATH_IMAGE076
And expressing the point coordinates in the axis point gluing track visual model under the current mechanical axis coordinate system.
And 7, calculating absolute mechanical axis coordinates of coordinate points in the dispensing track visual model, wherein the method comprises the following steps:
step 7.1, calculating the central point of the image
Figure 554426DEST_PATH_IMAGE077
To the 4 th step, the coordinates of the template center point image
Figure 69721DEST_PATH_IMAGE078
Mechanical inter-axle distance coordinate of
Figure 789415DEST_PATH_IMAGE079
The mechanical inter-axle distance coordinate
Figure 36857DEST_PATH_IMAGE080
The calculation formula of (a) is as follows:
Figure 98671DEST_PATH_IMAGE082
(8)
7.2, calculating absolute mechanical axis coordinates of each coordinate point in the final dispensing track visual model and stuffing the absolute mechanical axis coordinates into an array
Figure 876134DEST_PATH_IMAGE083
In, and
Figure 294477DEST_PATH_IMAGE084
Figure 852497DEST_PATH_IMAGE085
visual model representing dispensing trajectory
Figure 444016DEST_PATH_IMAGE042
The absolute mechanical coordinate point is set to be the absolute mechanical coordinate point,
Figure 75985DEST_PATH_IMAGE085
the calculation formula of (a) is as follows:
Figure 993126DEST_PATH_IMAGE086
(9)
in step 5 and 6, see fig. 3, the image coordinate system is
Figure 710546DEST_PATH_IMAGE002
The coordinate system 0 point is established at the upper left corner of the image, the x-axis direction and the y-axis direction are based on the rows and the columns of the image, the x-axis direction and the y-axis direction are orthogonal, the x-axis and the y-axis dimensions are pixels, and the unit of the pixel is pixel; the symbol i is used to distinguish different coordinate systems, and i is the first letter of an image.
And 8, outputting the model coordinate points, and executing coordinate dispensing by the lower computer: and outputting the target coordinate point calculated in the step 6 to lower computer software to perform dispensing.
It should be noted that, in the 4 th step, the 5 th step, the 6 th step, the 7 th step and the 8 th step, the guided repositioning of the established visual model of the dispensing trajectory can be used among different devices of the same type.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical scope of the present invention and the equivalent alternatives or modifications according to the technical solution and the inventive concept of the present invention within the technical scope of the present invention.

Claims (10)

1. A cross-platform visual guide dispensing guide method is characterized by comprising the following steps:
step 1, collecting images: placing the product at the center of the image view, and adjusting parameters of a light source, a camera and a lens until the product image is clear and the contrast is clear;
step 2, drawing a characteristic area, and creating a matching positioning template: drawing a characteristic region on a reference image, creating a matching template, and calculating the mechanical axis coordinate of a template central point according to the mechanical axis coordinate of a camera, a camera calibration matrix and the image coordinate of the template central point during reference image acquisition;
step 3, teaching a glue path, and generating a visual model of a glue dispensing track: moving a camera shaft, aligning the central point of the image to the top point of the contour to be taught on the glue path, recording the coordinate of the mechanical shaft at the moment, and generating a visual model of the glue dispensing track by combining the coordinate of the mechanical shaft of the central point of the template in the step 2;
step 4, searching a matching template: searching a matching template, positioning the image coordinate of the center point of the template, and recording the mechanical axis coordinate when the image is taken currently;
and 5, transferring the model to an image coordinate system: combining the dispensing track visual model in the step 3 and the template central point image coordinates in the step 4, calculating a pixel scale according to a current equipment camera calibration matrix, and converting the dispensing track visual model into an image coordinate system;
and 6, transferring the image coordinate system to a mechanical axis coordinate system: according to the current equipment camera calibration matrix, the dispensing track visual model is converted from an image coordinate system to a mechanical axis coordinate system, and a target coordinate point of the mechanical axis to be moved is solved;
7, calculating absolute mechanical axis coordinates of coordinate points in the dispensing track visual model;
and 8, outputting the model coordinate points, and executing coordinate dispensing by the lower computer: and outputting the target coordinate point calculated in the step 6 to lower computer software to perform dispensing.
2. The cross-platform visual guidance dispensing guiding method according to claim 1, characterized in that: the camera is mounted on a camera shaft and moves synchronously with the camera shaft.
3. The cross-platform visual guidance dispensing guiding method according to claim 1, characterized in that: in the step 2, an image is obtained according to the step 1, a template region of interest is drawn in the image and used as a template region to create a template, and the current image is the reference image.
4. The cross-platform visual guidance dispensing guiding method according to claim 1, characterized in that: in the step 3, the mechanical axis coordinate system is
Figure 33917DEST_PATH_IMAGE001
And the coordinate system 0 point is established at the original position of the mechanical axis x and y reset points, the directions of the x and y axes are based on the installation direction of the mechanical axis, the directions of the x axis and the y axis are orthogonal, and the dimension of the x axis and the y axis is length.
5. The cross-platform visual guidance dispensing guide method according to claim 4, characterized in that: in the 5 th step and the 6 th step, the image coordinate system is
Figure 702796DEST_PATH_IMAGE003
And the coordinate system 0 point is established at the upper left corner of the image, the x-axis direction and the y-axis direction are based on the rows and the columns of the image, the x-axis direction and the y-axis direction are orthogonal, and the x-axis and the y-axis are pixels.
6. The cross-platform visual guidance dispensing guiding method according to claim 1, characterized in that: in the step 3, the contour vertex coordinates of the dispensing trajectory visual model are all based on a model coordinate system.
7. The cross-platform visual guidance dispensing guide method according to claim 6, characterized in that: the coordinate system of the model is
Figure 509209DEST_PATH_IMAGE005
And establishing a coordinate system 0 point on the central point of the matching template in the step 2, wherein the x-axis direction and the y-axis direction are orthogonal based on the rows and the columns of the image, and the x-axis scale and the y-axis scale are lengths.
8. The cross-platform visual guidance dispensing guide method according to claim 5, characterized in that: in the 2 nd step, the camera calibration matrix is expressed as: image coordinate system during plane motion of mechanical axis
Figure 325855DEST_PATH_IMAGE006
Transferring the moving distance to a mechanical axis coordinate system
Figure 62867DEST_PATH_IMAGE001
And moving the relation matrix between the intervals downwards.
9. The cross-platform visual guidance dispensing guide method according to claim 6, characterized in that: in the step 3, the calculation of each vertex model coordinate on the visual model contour of the dispensing trajectory comprises the following steps:
first, the
Figure 399301DEST_PATH_IMAGE007
Calculating the displacement of each vertex of the contour of the rubber road relative to the coordinate of the mechanical axis of the camera when the reference image is collected;
first, the
Figure 829146DEST_PATH_IMAGE008
Step (A) to
Figure 133088DEST_PATH_IMAGE007
Transferring the displacement obtained by calculation in the step to an image coordinate system to obtain a converted point;
first, the
Figure 221261DEST_PATH_IMAGE009
Step (A) to
Figure 864732DEST_PATH_IMAGE008
And transferring the converted points obtained in the step to a model coordinate system, and finally obtaining each vertex model coordinate on the outline of the visual model of the dispensing track.
10. The cross-platform visual guidance dispensing guiding method according to claim 1, characterized in that: in the 4 th step, the 5 th step, the 6 th step, the 7 th step and the 8 th step, the guiding relocation of the established visual model of the dispensing trajectory can be used among different devices of the same type.
CN202210262967.1A 2022-03-17 2022-03-17 Cross-platform visual guide dispensing guiding method Active CN114359393B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210262967.1A CN114359393B (en) 2022-03-17 2022-03-17 Cross-platform visual guide dispensing guiding method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210262967.1A CN114359393B (en) 2022-03-17 2022-03-17 Cross-platform visual guide dispensing guiding method

Publications (2)

Publication Number Publication Date
CN114359393A true CN114359393A (en) 2022-04-15
CN114359393B CN114359393B (en) 2022-05-17

Family

ID=81095018

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210262967.1A Active CN114359393B (en) 2022-03-17 2022-03-17 Cross-platform visual guide dispensing guiding method

Country Status (1)

Country Link
CN (1) CN114359393B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115830147A (en) * 2023-02-20 2023-03-21 常州铭赛机器人科技股份有限公司 Transfer printing and dispensing rotation center calibration method based on monocular vision

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112735969A (en) * 2021-04-02 2021-04-30 惠州高视科技有限公司 LED semiconductor packaging glue dispensing defect detection method, electronic equipment and storage medium
CN113070876A (en) * 2021-03-19 2021-07-06 深圳群宾精密工业有限公司 Manipulator dispensing path guiding and deviation rectifying method based on 3D vision
CN113284191A (en) * 2021-06-10 2021-08-20 广东奥普特科技股份有限公司 Dispensing method, system, equipment and storage medium based on visual guidance

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113070876A (en) * 2021-03-19 2021-07-06 深圳群宾精密工业有限公司 Manipulator dispensing path guiding and deviation rectifying method based on 3D vision
CN112735969A (en) * 2021-04-02 2021-04-30 惠州高视科技有限公司 LED semiconductor packaging glue dispensing defect detection method, electronic equipment and storage medium
CN113284191A (en) * 2021-06-10 2021-08-20 广东奥普特科技股份有限公司 Dispensing method, system, equipment and storage medium based on visual guidance

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115830147A (en) * 2023-02-20 2023-03-21 常州铭赛机器人科技股份有限公司 Transfer printing and dispensing rotation center calibration method based on monocular vision

Also Published As

Publication number Publication date
CN114359393B (en) 2022-05-17

Similar Documents

Publication Publication Date Title
CN112132894B (en) Mechanical arm real-time tracking method based on binocular vision guidance
CN105014677B (en) Vision Mechanical arm control method based on Camshift visual tracking and D-H modeling algorithm
CN111801198B (en) Hand-eye calibration method, system and computer storage medium
CN107471218B (en) Binocular vision-based hand-eye coordination method for double-arm robot
CN110717943A (en) Method and system for calibrating eyes of on-hand manipulator for two-dimensional plane
CN108492017B (en) Product quality information transmission method based on augmented reality
CN110142770B (en) Robot teaching system and method based on head-mounted display device
Gratal et al. Visual servoing on unknown objects
CN114310901B (en) Coordinate system calibration method, device, system and medium for robot
CN113362452A (en) Hand gesture three-dimensional reconstruction method and device and storage medium
CN114359393B (en) Cross-platform visual guide dispensing guiding method
CN106651958B (en) Object recognition device and method for moving object
CN114519738A (en) Hand-eye calibration error correction method based on ICP algorithm
TW201538925A (en) Non-contact measurement device and method for object space information and the method thereof for computing the path from capturing the image
CN110017852A (en) A kind of navigation positioning error measurement method
CN112109069A (en) Robot teaching device and robot system
CN109284407B (en) Device for training automatic labeling data set of intelligent sales counter
CN115008454A (en) Robot online hand-eye calibration method based on multi-frame pseudo label data enhancement
CN107990825B (en) High-precision position measuring device and method based on priori data correction
CN114511690A (en) 3D target detection data set acquisition device and labeling method
CN113172659B (en) Flexible robot arm shape measuring method and system based on equivalent center point identification
CN113393524A (en) Target pose estimation method combining deep learning and contour point cloud reconstruction
Morbidi et al. Phase correlation for dense visual compass from omnidirectional camera-robot images
JP2021021577A (en) Image processing device and image processing method
CN114926542A (en) Mixed reality fixed reference system calibration method based on optical positioning 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