CN112172191B - Robot glue scraping method based on visual identification - Google Patents
Robot glue scraping method based on visual identification Download PDFInfo
- Publication number
- CN112172191B CN112172191B CN202011006479.1A CN202011006479A CN112172191B CN 112172191 B CN112172191 B CN 112172191B CN 202011006479 A CN202011006479 A CN 202011006479A CN 112172191 B CN112172191 B CN 112172191B
- Authority
- CN
- China
- Prior art keywords
- processed
- pipe
- glue scraping
- image
- visual
- 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.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C70/00—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts
- B29C70/04—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts comprising reinforcements only, e.g. self-reinforcing plastics
- B29C70/28—Shaping operations therefor
- B29C70/30—Shaping by lay-up, i.e. applying fibres, tape or broadsheet on a mould, former or core; Shaping by spray-up, i.e. spraying of fibres on a mould, former or core
- B29C70/32—Shaping by lay-up, i.e. applying fibres, tape or broadsheet on a mould, former or core; Shaping by spray-up, i.e. spraying of fibres on a mould, former or core on a rotating mould, former or core
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C70/00—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts
- B29C70/04—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts comprising reinforcements only, e.g. self-reinforcing plastics
- B29C70/28—Shaping operations therefor
- B29C70/30—Shaping by lay-up, i.e. applying fibres, tape or broadsheet on a mould, former or core; Shaping by spray-up, i.e. spraying of fibres on a mould, former or core
- B29C70/38—Automated lay-up, e.g. using robots, laying filaments according to predetermined patterns
- B29C70/382—Automated fiber placement [AFP]
- B29C70/384—Fiber placement heads, e.g. component parts, details or accessories
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C70/00—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts
- B29C70/04—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts comprising reinforcements only, e.g. self-reinforcing plastics
- B29C70/28—Shaping operations therefor
- B29C70/54—Component parts, details or accessories; Auxiliary operations, e.g. feeding or storage of prepregs or SMC after impregnation or during ageing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29L—INDEXING SCHEME ASSOCIATED WITH SUBCLASS B29C, RELATING TO PARTICULAR ARTICLES
- B29L2023/00—Tubular articles
- B29L2023/22—Tubes or pipes, i.e. rigid
Abstract
The invention discloses a robot glue scraping method based on visual identification, which belongs to the field of glue scraping methods and comprises the following steps: the method comprises the steps that a visual recognition device obtains an image of a pipe to be processed, the image is processed through a visual image processing algorithm to obtain the diameter and the perimeter L of the pipe to be processed and the curvature of the circumference of the pipe to be processed; according to the curvature information, the position of a glue scraping mechanism on a mechanical arm in a glue scraping system is adjusted, so that a glue scraping roller brush is positioned to the topmost end of a pipe to be processed, and moves downwards to the lowest point along the curvature route of the pipe to be processed from the topmost end to the lowest point to finish a first half-circumference glue scraping action, a second driving device starts to drive the mechanical arm to move by the width of a rolling brush, and the first half-circumference glue scraping action is returned to the first step of cyclic processing again until the first half surface of the pipe to be processed is finished; and rotating the pipe to be processed, and returning to the step one for circular treatment until the second half surface of the pipe to be processed is scraped. The invention can automatically complete the glue scraping action by adopting the glue scraping system, and is safe and environment-friendly.
Description
Technical Field
The invention relates to the field of a glue scraping method, in particular to a robot glue scraping method based on visual identification.
Background
In the process of manufacturing the pipe made of the resin material and winding the glass fiber reinforced plastic fiber yarns on the core column, chemical viscose glue is required to be continuously added to solidify the pipe into an integral pipe. In the manufacturing process, when one layer of glass fiber reinforced plastic fiber is wound, redundant viscose flows down along the cylindrical surface, chemical viscose causes pollution to the environment, and residual glue on the pipe is not uniform; the emitted toxic gas can injure workers in field operation and cause waste of raw materials of production enterprises.
The enterprise manufacturing the pipe at the present stage adopts manual operation to complete the process, and has several problems: firstly, occupational disease hazards such as respiratory diseases are brought to workers in severe environment; secondly, manual operation is not accurate enough, causes the viscose outflow, causes the pollution to the environment. Thirdly, manual operation is not standard, which causes adhesive waste and uneven thickness of the glue on the surface of the pipe, and affects the quality of the pipe.
Disclosure of Invention
The invention aims to solve at least one technical problem in the prior art and provides a robot glue scraping method based on visual identification.
The technical solution of the invention is as follows:
a robot glue scraping method based on visual identification comprises the following steps:
the method comprises the following steps: the method comprises the steps that a visual recognition device obtains an image of a pipe to be processed, the image is processed through a visual image processing algorithm to obtain the diameter D of the pipe to be processed, and the perimeter L of the pipe to be processed and the curvature of the circumference of the pipe to be processed are calculated;
step two: according to the curvature information in the step one, the position of a glue scraping mechanism on a mechanical arm in a glue scraping system is adjusted, so that a glue scraping roller brush is positioned to the topmost end of the pipe to be processed, and from the topmost end, the glue scraping roller brush moves downwards to the lowest point along the curvature route of the pipe to be processed, and a first half-circumference glue scraping action is completed;
step three: the mechanical arm moves by the width of one rolling brush and returns to the step I for cyclic treatment again until the first half surface of the pipe to be processed is scraped;
step four: and rotating the pipe to be processed, and returning to the step one for circular treatment until the second half surface of the pipe to be processed is scraped.
Preferably, the visual image processing algorithm specifically includes:
s1: the visual recognition device collects the image information of the pipe to be processed;
s2: performing error compensation processing on the image information in S1 to obtain a corrected image;
s3: extracting and analyzing the corrected image in the S2 to obtain the circumferential edge information of the pipe to be processed;
s4: and performing fitting calculation on the circumferential edge information in the S3 to obtain the diameter of the pipe to be processed.
Preferably, in S2, the error compensation method specifically includes:
in the visual field of the visual identification device, a point (x, y) on the pipe to be processed is positioned at a certain point (u, v) on the image information, and the following relational expression exists according to the cause of imaging distortion error:
in the formula aij,bijIs the coefficient of a polynomial, and n is the degree of the polynomial; i, j is a number representing the number of iterations in the pixel domain.
Preferably, in S3, the specific method for extraction and analysis is as follows: carrying out gray level processing on the corrected image, acquiring a gray level histogram, setting a gray level threshold value, and carrying out image segmentation on the gray level histogram; scanning the segmented image, marking a pixel currently being scanned, checking connectivity of the pixel and a plurality of adjacent pixels scanned previously, if the pixel is connected, marking the pixel as the same region symbol, and if the pixel is not connected, distinguishing the pixel; after marking of each area is finished, judging the marked area to which the image center belongs, obtaining a mark number, obtaining a boundary image point corresponding to the area, and extracting an edge preliminary outline of the pipe to be processed; and finally, accurately searching the preliminary edge profile to determine the accurate edge profile, thereby obtaining the circumferential edge information of the pipe to be processed.
Preferably, the precise search employs eight-domain precise search.
Preferably, in S4, the fitting calculation specifically includes: according to the circumferential edge information of the pipe to be processed, determining the coordinates of the edge point set points, and obtaining a correction coordinate point (x) after correcting and converting the coordinatesi,yi) The coordinates of the circle center are (A, B), the radius of the circle is set as r, the radius is calculated according to the equation of the circle, and the equation specifically comprises the following steps:
(xi-A)2+(yi-B)2=r2。
preferably, the least square fitting is also performed on the corrected circumferential edge information; the following formula is obtained, specifically: (x)i-A)2+(yi-B)2=r2;
When at least 3 characteristic points are acquired by the vision acquisition device, the numerical value is substituted into the above formula to obtain the following matrix formula:
after the optimal solution of a, b and c in the coefficient array is obtained, the coordinates of the circle center are as follows:having a diameter D of
The invention has the following beneficial effects: according to the robot frictioning method based on visual identification, the image information of the pipe to be processed is obtained through the visual identification device, after the image information is subjected to image processing and analysis, the diameter, the circumference and the curvature of the pipe to be processed are obtained, the mechanical arm is adjusted in position according to the information, so that frictioning action of the pipe to be processed is realized, automatic frictioning is realized, meanwhile, the problem that frictioning operation is difficult due to uneven residual glue thickness on the wall of the pipe is solved, and the robot frictioning method can be applied to frictioning on different-diameter pipes; more intelligent frictioning action is realized.
Drawings
FIG. 1 is a flow chart of an image detection algorithm of the present invention;
FIG. 2 is a first search graph of an eight-neighborhood refinement search of the present invention;
FIG. 3 is a diagram of a second search in an eight neighborhood refinement search of the present invention;
FIG. 4 is a block diagram of a pixel edge point search routine of the present invention
FIG. 5 is a first schematic structural diagram of a preferred embodiment of the present invention;
FIG. 6 is a second schematic structural view of the preferred embodiment of the present invention;
FIG. 7 is an enlarged view of part A of FIG. 6;
FIG. 8 is a side view of FIG. 6;
FIG. 9 is a schematic structural view of a second driving device in a preferred embodiment of the present invention;
FIG. 10 is an enlarged view of part B of FIG. 9;
in the figure, 100-a machine frame, 200-a positioning mandrel, 300-a driving roller, 400-a visual recognition device, 500-a glue scraping mechanism, 501-a glue scraping roller brush, 502-a glue storage cylinder, 600-a mechanical arm, 601-a first rotating mechanism, 602-a first rotating arm, 700-a second driving device, 701-a servo motor, 702-a gear, 703-a rack, 704-a sliding rail and 705-a movable plate.
Detailed Description
Reference will now be made in detail to the present embodiments of the present invention, preferred embodiments of which are illustrated in the accompanying drawings, wherein the drawings are provided for the purpose of visually supplementing the description in the specification and so forth, and which are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
Refer to fig. 1 to 10.
The invention provides a glue scraping system based on visual identification,
a frame 100; the frame 100 is provided with a positioning mandrel 200 and a first driving device for driving the positioning mandrel 200 to rotate;
the gluing device comprises a gluing mechanism 500, a mechanical arm 600 and a second driving device 700 for driving the mechanical arm 600 to move back and forth along the axial direction of the positioning mandrel 200;
a visual recognition device 400 disposed on the robot arm 600.
In this embodiment, the diameter of the pipe to be processed is obtained through the visual recognition device 400, the circumference of the pipe is calculated, the mechanical arm 600 starts to perform frictioning treatment on the pipe to be processed according to the identification information of the visual recognition device 400, the completion of the half circumference corresponding to one frictioning rolling brush is a cycle end, the second driving device 700 starts to drive the mechanical arm 600 to move, the visual recognition device re-identifies the diameter of the pipe to be processed, the rolling brush positioning is started, frictioning on the next step starts, and cycle operation is performed in sequence, when the end of the pipe corresponding to the first radius is completed, the first driving device drives the positioning mandrel 200 to rotate the pipe to be processed to the second radius surface, and frictioning operation is continued according to the method. The pipe to be processed in the embodiment is a glass fiber reinforced plastic pipe.
As an embodiment of the present invention, it may also have the following additional technical features:
first drive arrangement includes the motor and sets up in the roller set at frame 100 both ends, the roller set includes two drive rollers 300 at least, and the interval between two drive rollers 300 is less than the diameter of waiting to process tubular product, the motor can drive roller 300 rotates.
The second driving device 700 comprises a servo motor 701 and a sliding rail 704 arranged in parallel with the positioning mandrel 200, a rack 703 is arranged at the side end of the sliding rail 704, a gear 702 meshed with the rack 703 is arranged at the output end of the servo motor 701, a movable plate 705 is arranged on the sliding rail 704 in a sliding manner, and the mechanical arm 600 is arranged on the movable plate 705.
The vision recognition device 400 is a vision camera, the setting can enable the glue scraping to be more accurate, the vision camera obtains the diameter of the pipe to be processed, the perimeter of the pipe is calculated, and therefore the mechanical arm conducts accurate glue scraping according to the perimeter.
The mechanical arm 600 adopts a six-shaft mechanical arm, so that the movement precision is more sensitive, namely, the mechanical arm is more flexible, a first rotating mechanism 601 is arranged at the front end of the mechanical arm, the flexible glue scraping action is realized through the six-shaft mechanical arm 600, and the mechanical arm is combined with a second driving device to realize automatic operation.
The visual recognition device 400 is disposed on the first rotating mechanism 601 to realize that the visual recognition device 400 moves along with the first rotating mechanism 601.
The glue scraping mechanism 500 is disposed on the first rotating mechanism 601 to realize that the glue scraping mechanism 400 moves along with the first rotating mechanism 601.
Specifically, the first rotating mechanism may be hinged to move up and down on the first rotating arm 602, or may be connected in other forms of rotation, but is not limited to this
In some applications, the glue scraping mechanism 500 comprises a glue scraping roller brush 501 and a glue storage cylinder 502, the glue scraping roller brush 501 is positioned above the glue storage cylinder 502, and the arrangement can collect scraped glue while performing glue scraping operation, is more beneficial to centralized treatment and recovery, and avoids waste; specifically, the second driving device 700 drives the mechanical arm 600 to move by the width of one glue scraping roller brush 501.
The robot further comprises a control device, wherein the control device can control the actions of the robot arm 600, the first driving device and the second driving device 700 according to the identification signal of the visual identification device 400, and specifically, controls the actions of the robot arm 600, the motor and the servo motor 701 so as to realize automation.
The invention also provides a glue scraping method applied to the glue scraping system, which comprises the following steps:
the method comprises the following steps:
the method comprises the following steps: the method comprises the steps that a visual recognition device obtains an image of a pipe to be processed, the image is processed through a visual image processing algorithm to obtain the diameter D of the pipe to be processed, and the perimeter L of the pipe to be processed and the curvature of the circumference of the pipe to be processed are calculated; l ═ pi D ═ 2 pi r, where: d is the diameter and r is the radius.
The curvature is the rotation rate of a tangential direction angle alpha to an arc length s of a certain point on a curve, and is defined by differentiation, and the degree of deviation of the curve from a straight line is indicated.
When K is lim | Δ α/Δ s | and Δ s tends to be 0, it is defined that K is curvature.
Step two: according to the curvature information in the step one, the position of a glue scraping mechanism on a mechanical arm in a glue scraping system is adjusted, so that a glue scraping roller brush is positioned to the topmost end of the pipe to be processed, and from the topmost end, the glue scraping roller brush moves downwards to the lowest point along the curvature route of the pipe to be processed, and a first half-circumference glue scraping action is completed;
step three: the second driving device starts to drive the mechanical arm to move by the width of one rolling brush, and the step one is returned again to the step one for circular treatment until the first half surface of the pipe to be processed is scraped;
step four: and rotating the pipe to be processed, and returning to the step one for circular treatment until the second half surface of the pipe to be processed is scraped.
The visual image processing algorithm specifically comprises:
s1: the visual recognition device 400 collects the image information of the pipe to be processed;
s2: performing error compensation processing on the image information in S1 to obtain a corrected image;
s3: extracting and analyzing the correction image in the S2 to obtain the circumferential edge information of the pipe to be processed;
s4: and performing fitting calculation on the circumferential edge information in the S3 to obtain the diameter of the pipe to be processed.
In S2, the error compensation method specifically includes:
in the visual field of the visual recognition device 400, a point (x, y) on the pipe to be processed is located at a certain point (u, v) on the image information, and the following relation exists according to the cause of the imaging distortion error:
in the formula aij,bijIs the coefficient of a polynomial, and n is the degree of the polynomial; i, j is a number representing the number of iterations in the pixel domain.
In S3, the specific method for extraction and analysis includes: carrying out gray level processing on the corrected image, acquiring a gray level histogram, setting a gray level threshold value, and carrying out image segmentation on the gray level histogram; scanning the segmented image, marking the current scanned pixel and checking the connectivity of the pixel and a plurality of scanned neighbor pixels, wherein the connectivity means whether the pixels are connected or not and whether the pixels are connected into a piece or not, and if the pixels are disconnected, the connectivity is not good; if the two are connected, the two are marked as the same region symbol, and if the two are not connected, the two are distinguished; after marking of each region is finished, judging the marked region to which the image center belongs, obtaining a boundary image point corresponding to the region after the mark number is obtained, and extracting an edge preliminary contour of the pipe to be processed; and finally, accurately searching the preliminary edge profile to determine the accurate edge profile, thereby obtaining the circumferential edge information of the pipe to be processed.
The accurate search adopts eight-field accurate search. The specific method comprises the following steps:
in the first search, the image is traversed to find the first non-zero pixel point, and then the point is certainly the boundary point. And setting the point as a starting point m, and clockwise searching a first nonzero pixel point m '(the point m' is also a boundary point) encountered in the eight neighborhoods of the point. And (5) setting m to be m ', and then performing clockwise search in the neighborhood, wherein the starting point of the search is the zero point before m ' in the process from m to m '.
In FIG. 2, at point m, the search is performed in the order of 0-1-2-3-4 … …. If the point 6 is the first non-zero pixel point found, the point 6 in the figure is a boundary point, the starting position of m ' search is 5 in fig. 2, that is, 4 corresponding to m ', and the search sequence of m ' is 4-5-6-7-0-1-2-3.
The same principle can be known; when m' is 2 and 3, searching for the starting point to be 0; when m' is 4, 5, searching for the starting point to be 2; when m' is 6, 7, searching for a starting point of 4; when m' is 0, 1, the search starting point is 6.
May be stored with a map mapping.
Map[0]=6,map[1]=6;map[2]=0,map[3]=0;map[4]=2,map[5]=2,Map[6]=4,map[7]=4。
If the last step finds a value d (d is 6 in fig. 2), then the initial value j ═ map [ d ] (map [6] ═ 4, i.e., j;, 4;), is set, but the search is continued for 0, 1, 2, and 3, so the remainder of the division by 8 is taken here. d is set to (d + i)/8(i is 0, 1, 2 … … 8), and the operation logic diagram is shown in fig. 4.
In S4, the fitting calculation specifically includes: according to the circumferential edge information of the pipe to be processed, determining the coordinates of the edge point set points, and obtaining a correction coordinate point (x) after correcting and converting the coordinatesi,yi) The coordinates of the circle center are (A, B), the radius of the circle is set as r, if no error exists, the radius is calculated according to the equation of the circle, and the equation specifically comprises the following steps: (x)i-A)2+(yi-B)2=r2;
Because the size of the actual pipe to be processed cannot be an absolute circle, and certain points do not fall on the circumference, optimization is needed when the circumference is fitted, so that the fitted result is closest to a true value. The commonly used fitting method is the least square method, and the main idea is to solve coefficients so that the sum of the squares of the residuals of the equations is minimal. The corrected circumferential edge information is subjected to least square fitting; the following formula is obtained, specifically:
when at least 3 characteristic points are acquired by the vision acquisition device, the numerical value is substituted into the above formula to obtain the following matrix formula:
after the optimal solution of the coefficient array is obtained, the coordinates of the circle center are as follows:having a diameter D of
The method comprises the steps that image information of a pipe to be processed is obtained through a visual recognition device, after the image information is processed and analyzed, the diameter, the circumference and the curvature of the pipe to be processed are obtained, a mechanical arm is adjusted in position according to the image information, so that the glue scraping action of the pipe to be processed is realized, automatic glue scraping is realized, the diameter information of the pipe to be processed is obtained through the visual recognition device, the posture of the mechanical arm is adjusted in real time, the problem that glue remaining on the wall of the pipe is uneven in thickness and difficult to scrape is solved, and meanwhile, the method can be applied to glue scraping on different-diameter pipes; more intelligent frictioning action is realized.
The above additional technical features can be freely combined and used in superposition by those skilled in the art without conflict.
The above description is only a preferred embodiment of the present invention, and all technical solutions that can achieve the object of the present invention by substantially the same means are within the protection scope of the present invention.
Claims (6)
1. A robot glue scraping method based on visual identification is characterized in that: the method comprises the following steps:
the method comprises the following steps: the method comprises the steps that a visual recognition device obtains an image of a pipe to be processed, the image is processed through a visual image processing algorithm to obtain the diameter D of the pipe to be processed, and the perimeter L of the pipe to be processed and the curvature of the circumference of the pipe to be processed are calculated;
step two: according to the curvature information in the step one, the position of a glue scraping mechanism on a mechanical arm in a glue scraping system is adjusted, so that a glue scraping roller brush is positioned to the topmost end of the pipe to be processed, and from the topmost end, the glue scraping roller brush moves downwards to the lowest point along the curvature route of the pipe to be processed, and a first half-circumference glue scraping action is completed;
step three: the mechanical arm moves for the width of one rolling brush, and the step one is returned to the step one for circular treatment until the first half surface of the pipe to be processed is scraped;
step four: rotating the pipe to be processed, and returning to the step I for circular treatment again until the second half surface of the pipe to be processed is scraped; the visual image processing algorithm specifically comprises:
s1: the visual recognition device collects the image information of the pipe to be processed;
s2: performing error compensation processing on the image information in S1 to obtain a corrected image;
s3: extracting and analyzing the corrected image in the S2 to obtain the circumferential edge information of the pipe to be processed;
s4: and performing fitting calculation on the circumferential edge information in the S3 to obtain the diameter of the pipe to be processed.
2. The robot glue scraping method based on the visual recognition is characterized in that: in S2, the error compensation method specifically includes:
in the visual field of the visual identification device, a point (x, y) on the pipe to be processed is positioned at a certain point (u, v) on the image information, and the following relational expression exists according to the cause of imaging distortion error:
in the formula aij,bijIs a coefficient of a polynomialN is the degree of a polynomial; i, j is a number representing the number of iterations in the pixel domain.
3. The robot glue scraping method based on the visual recognition is characterized in that: in S3, the specific method for extraction and analysis includes: carrying out gray level processing on the corrected image, acquiring a gray level histogram, setting a gray level threshold value, and carrying out image segmentation on the gray level histogram; scanning the segmented image, marking a current scanned pixel, checking the connectivity of the pixel and a plurality of scanned neighbor pixels, if the pixel is connected, marking the pixel as the same region symbol, and if the pixel is not connected, distinguishing the pixels; after marking of each region is finished, judging the marked region to which the image center belongs, obtaining a boundary image point corresponding to the region after the mark number is obtained, and extracting an edge preliminary contour of the pipe to be processed; and finally, accurately searching the preliminary edge profile to determine the accurate edge profile so as to obtain the circumferential edge information of the pipe to be processed.
4. The robot glue scraping method based on the visual recognition is characterized in that: the accurate search adopts eight-neighborhood accurate search.
5. The robot glue scraping method based on the visual recognition is characterized in that: in S4, the fitting calculation specifically includes: according to the circumferential edge information of the pipe to be processed, determining the coordinates of the edge point set points, and obtaining a correction coordinate point (x) after correcting and converting the coordinatesi,yi) The coordinates of the circle center are (A, B), the radius of the circle is set as r, the radius is calculated according to the equation of the circle, and the equation specifically comprises the following steps: (x)i-A)2+(yi-B)2=r2。
6. The robot glue scraping method based on the visual recognition is characterized in that: the least square fitting is also needed to be carried out on the corrected circumferential edge information; the following formula is obtainedComprises the following steps: (x)i-A)2+(yi-B)2=r2;
When at least 3 characteristic points are acquired by the vision acquisition device, the numerical value is substituted into the above formula to obtain the following matrix formula:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011006479.1A CN112172191B (en) | 2020-09-23 | 2020-09-23 | Robot glue scraping method based on visual identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011006479.1A CN112172191B (en) | 2020-09-23 | 2020-09-23 | Robot glue scraping method based on visual identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112172191A CN112172191A (en) | 2021-01-05 |
CN112172191B true CN112172191B (en) | 2022-06-17 |
Family
ID=73956496
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011006479.1A Active CN112172191B (en) | 2020-09-23 | 2020-09-23 | Robot glue scraping method based on visual identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112172191B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113318917A (en) * | 2021-06-18 | 2021-08-31 | 深圳市裕同包装科技股份有限公司 | Automatic glue scraping device and method thereof |
CN115167288B (en) * | 2022-09-08 | 2022-12-20 | 深圳市世宗自动化设备有限公司 | Pressure self-adaptive glue scraping method and system |
CN116809572B (en) * | 2023-08-30 | 2023-12-12 | 潍坊泽成生物技术有限公司 | Automatic change experiment test tube cleaning system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106733525A (en) * | 2016-11-24 | 2017-05-31 | 杭州力视科技有限公司 | A kind of method and device of the automatically dropping glue based on dual camera |
CN206276576U (en) * | 2016-12-15 | 2017-06-27 | 宁德时代新能源科技股份有限公司 | Frictioning device |
-
2020
- 2020-09-23 CN CN202011006479.1A patent/CN112172191B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106733525A (en) * | 2016-11-24 | 2017-05-31 | 杭州力视科技有限公司 | A kind of method and device of the automatically dropping glue based on dual camera |
CN206276576U (en) * | 2016-12-15 | 2017-06-27 | 宁德时代新能源科技股份有限公司 | Frictioning device |
Also Published As
Publication number | Publication date |
---|---|
CN112172191A (en) | 2021-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112172191B (en) | Robot glue scraping method based on visual identification | |
CN108332681B (en) | A kind of determination method of the big plastic bending sectional profile curve lin of thin-wall pipes | |
CN110728667A (en) | Automatic and accurate cutter wear loss measuring method based on gray level image probability | |
CN110068274B (en) | Adhesive tape detection demonstration method for gluing sensor | |
CN110091217B (en) | Turning flutter acceleration acquisition system and method based on machine vision | |
CN212312827U (en) | Automatic frictioning system with visual identification robot | |
CN104985332B (en) | Closed detection method of laser cutting machine | |
CN111062940A (en) | Screw positioning and identifying method based on machine vision | |
CN109540026B (en) | Application method of intelligent detection system for aviation nonstandard conduit | |
CN113112496B (en) | Sub-pixel shaft part size measurement method based on self-adaptive threshold | |
CN112558546B (en) | Online cutter parameter detection method based on computer vision | |
CN112767426B (en) | Target matching method and device and robot | |
CN111754422A (en) | Visual edge inspection method based on EDLines and LSM | |
CN115014217A (en) | Pipe online detection method based on laser ranging | |
CN110434932B (en) | Automatic trimming method for solar thin film flexible assembly | |
CN101524725A (en) | Detecting system and detecting method for shape precision of steel tube straightening machine | |
CN110189316B (en) | Automatic teaching method for adhesive tape detection | |
CN112060622A (en) | Automatic frictioning system with visual identification robot | |
CN113566735B (en) | Laser in-situ measurement method for rocket engine nozzle cooling channel line | |
CN116957943B (en) | Microscope stitching calibration method based on image fusion | |
US5563808A (en) | Pilger mill mandrel measuring device | |
CN217072627U (en) | Pipe production line's outward appearance detects removing devices | |
CN116228697A (en) | Steel bar part quality detection method based on unmanned aerial vehicle image point cloud data | |
CN115406899A (en) | Detection device and detection method suitable for surface defects of cylinder sleeves of different sizes | |
CN111397528B (en) | Portable train wheel regular section contour structure optical vision measurement system and method |
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 |