CN112975907B - Visual detection method for arc-shaped welding seam and adhesive tape - Google Patents
Visual detection method for arc-shaped welding seam and adhesive tape Download PDFInfo
- Publication number
- CN112975907B CN112975907B CN202110182543.XA CN202110182543A CN112975907B CN 112975907 B CN112975907 B CN 112975907B CN 202110182543 A CN202110182543 A CN 202110182543A CN 112975907 B CN112975907 B CN 112975907B
- Authority
- CN
- China
- Prior art keywords
- point
- central skeleton
- height
- central
- points
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 75
- 239000002390 adhesive tape Substances 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 230000000007 visual effect Effects 0.000 title claims abstract description 11
- 238000005070 sampling Methods 0.000 claims abstract description 55
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims abstract description 14
- 238000011179 visual inspection Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 2
- 238000003672 processing method Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000004026 adhesive bonding Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000004441 surface measurement Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/0081—Programme-controlled manipulators with master teach-in means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
- B25J13/087—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices for sensing other physical parameters, e.g. electrical or chemical properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a visual detection method for arc-shaped welding seams and adhesive tapes, which is characterized in that arc-shaped appearance point clouds of an object to be detected are obtained along a straight line and are converted into straight line appearance point clouds by the following steps: 1, determining an interested area, moving a selection frame, and recording an area with height information most similar to a teaching image as an evaluation area; 2) determining the position of a central skeleton point in an evaluation area, expanding on two sides of the central skeleton point by equal step length to obtain the height value of the corresponding point, and recording as a sampling point; 3) giving out a plane coordinate value corresponding to the height value of each sampling point according to the following rule; the abscissa is the offset between the sampling point and the corresponding central skeleton point; the ordinate is the distance between the central skeleton point corresponding to the sampling point and the first central skeleton point; the method can process the point cloud image of the arc welding seam/adhesive tape under the condition of collecting the image along the straight line, and convert the point cloud image from an arc shape to a straight line for being compatible with a straight line appearance point cloud processing method; the method has the advantages of simple drawing collection, good compatibility and easy realization.
Description
Technical Field
The invention relates to the technical field of three-dimensional visual detection, in particular to a visual detection method for arc-shaped welding seams and rubber strips.
Background
In the field of industrial manufacturing, the three-dimensional information of an object is crucial to the quality control of a production process, the three-dimensional surface measurement technology based on line structure light vision has the advantages of non-contact, high measurement precision and the like, automatic measurement can be realized through the cooperation of robots, and three-dimensional point cloud data of the surface of a measured object are scanned, so that a technical basis is provided for gluing detection and welding line detection in the automobile production process, and the three-dimensional point cloud data are increasingly applied to the industrial manufacturing process.
Generally, most of welding seams and rubber strips on the surface of a workpiece are linear, so that when quality analysis is carried out, a software algorithm analyzes the linear three-dimensional point cloud morphology based on linear point cloud characteristics, most of rubber strips/welding seams can be compatible, and the algorithm development difficulty can be reduced to a greater extent. However, the situation of a curved or arc-shaped adhesive tape/welding seam inevitably occurs in the industrial field, and for the adhesive tape/welding seam, the track of a robot is usually adjusted in the existing method, so that the emergent light plane of the structured light sensor is always perpendicular to the extending direction of the adhesive tape/welding seam, and then multi-row outline information is obtained through point cloud splicing. Because the light plane is always perpendicular to the trend of the adhesive tape/welding seam, the spliced adhesive tape/welding seam point cloud data is in a linear shape, and at the moment, the characteristics of the curved and arc adhesive tape/welding seam can be obtained by utilizing the existing linear point cloud analysis method. However, this method has the following disadvantages:
1) the robot needs to complete scanning of a curved object by walking an arc track, the method comprises the steps of firstly converting structured light plane coordinates into a robot tail end coordinate system through hand-eye calibration, then reading a tail end real-time pose in the scanning process of the robot, finally unifying the light plane coordinates into a base coordinate system according to the conversion relation between the robot tail end coordinate system and the base coordinate system, and realizing three-dimensional reconstruction based on the real-time pose of the robot; the method needs to convert the coordinate systems from the light plane to the tail end of the robot and from the tail end to the base coordinate system for many times, and because the conversion between each coordinate system has a calibration error, the errors can be introduced for many times;
2) the terminal pose of the robot needs to be acquired in real time, and the bottom layer development of the robot controller needs to be carried out, so that the development difficulty exists. The system is required to have higher real-time performance, the complexity of the system is increased, and errors can be introduced into the obtained real-time pose of the robot due to communication delay;
3) when the bending degree of the object to be measured (adhesive tape/welding seam) is large and is in the shape of C, S and the like, or the size of the object to be measured is small, the robot cannot adjust a proper track and cannot ensure that the emergent light plane of the structured light sensor is always vertical to the extending direction of the adhesive tape/welding seam because of the conditions of the size of the sensor, the interference of objects around the welded seam to be measured and the like.
Disclosure of Invention
In order to solve the problems, the invention provides a visual detection method for arc-shaped welding seams and adhesive tapes, which can process point cloud images of the arc-shaped welding seams/adhesive tapes under the condition of drawing along a straight line track, convert the point cloud images from an arc shape to a straight line and be compatible with a straight line shape point cloud processing method; the method has the advantages of simple drawing collection, good compatibility and simple and easily-realized calculation process.
Therefore, the technical scheme of the invention is as follows:
a visual detection method for arc welding seams and adhesive tapes is characterized in that a robot drives a structural optical sensor to scan the arc welding seams/adhesive tapes along a linear track to obtain arc-shaped appearance point clouds of a detected object, and the arc-shaped appearance point clouds are converted into linear appearance point clouds by the following steps:
1) determining an interested area of the point cloud image to be evaluated, moving a selection frame in the interested area based on the minimum detection frame size given by teaching to select an area most similar to the height information of the welding seam/adhesive tape in the point cloud image taught, and recording the area as an evaluation area; the minimum detection frame is a minimum area containing all welding seams/adhesive tapes on the teaching point cloud image;
2) determining the position of a central skeleton point on a welding seam/adhesive tape in an evaluation area by using a plane coordinate of the central skeleton point on the welding seam/adhesive tape in a minimum detection frame given by teaching, respectively taking the central skeleton point as a center, and extending towards two sides at equal intervals according to equal step length in a direction perpendicular to a connecting line of two adjacent central skeleton points to obtain the height value of the corresponding point, wherein the total width of the extension of the two sides is 130-250% of the width of the welding seam/adhesive tape obtained by teaching, and the extended point is marked as a sampling point;
the central skeleton point comprises a point manually marked at the position of the central line of the welding seam/adhesive tape during teaching and a point sequentially different from the two manually marked points by a step length A;
3) giving out a plane coordinate value corresponding to the height value of each sampling point according to the following rule;
the abscissa of the plane coordinate value is the offset of the sampling point compared with the corresponding central skeleton point;
the ordinate of the plane coordinate value is the distance between the central skeleton point corresponding to the sampling point and the first central skeleton point;
recording other central skeleton points except the first central skeleton point as skeleton points I, wherein the plane coordinate values of all the skeleton points I are (0, the distance between the skeleton point I and the first central skeleton point);
and all the corresponding height values and plane values and the first central skeleton point form a straight line shape point cloud.
Further, the method for judging the area most similar to the height information of the welding seam/adhesive tape in the teaching point cloud image in the step 1) comprises the following steps: obtaining S values corresponding to all the selection frames, and taking the selection frame corresponding to the minimum S value as an area most similar to the height information of the welding seam/adhesive tape in the teaching point cloud image;
p is 1,2 … … K, K represents the total number of central skeleton points;
g(p)the height difference mean value of the pth central skeleton point in the selected frame and the sampling point expanded according to the pth central skeleton point is obtained;
h(p)the height standard deviation of the p-th central skeleton point in the selection frame and the sampling point expanded according to the p-th central skeleton point is selected;
g(p)the height difference mean value of the p-th central skeleton point in the minimum detection frame on the teaching point cloud image and the sampling point expanded by the p-th central skeleton point is obtained;
h(p)the height standard deviation of the p-th central skeleton point in the minimum detection frame on the teaching point cloud image and the sampling point expanded by the p-th central skeleton point is calculated;
w1、w2weight, w, representing mean height difference, height standard deviation, respectively1+w2=1;
The height difference average value is the average value of the difference values of the heights of all other points and the reference point, wherein any point from the p-th central skeleton point and the extended sampling point is the reference point;
and the height standard deviation is the standard deviation of the difference value between the height value of the p-th central skeleton point and the extended sampling point and the height value of the reference point.
Further, the teaching process includes the steps of:
firstly, manually controlling a robot to drive a structured light sensor to scan arc-shaped welding seams/adhesive tapes along a straight track to obtain a point cloud image to be taught;
marking central skeleton points on the teaching point cloud image along the length direction of the welding seam/adhesive tape at the central line of the teaching point cloud image, and generating a plurality of central skeleton points between two adjacent central skeleton points by a step length A; acquiring a plane coordinate and a height value of each central skeleton point;
respectively taking the central framework point as a center, and expanding towards two sides at equal intervals according to equal step length in a direction perpendicular to a connecting line of two adjacent central framework points to obtain the height value of the corresponding point, wherein the total expanded width of the two sides is the width of a welding seam/adhesive tape, and the expanded points are marked as sampling points to obtain the height value of each sampling point;
marking the minimum area containing all welding seams/adhesive tapes and sampling points on the teaching point cloud image as a minimum detection frame;
calculating the average height difference of each central skeleton point and the expanded sampling points in the minimum detection frame and the height standard difference of each central skeleton point and the expanded sampling points;
the height difference mean value is the mean value of the difference values of the heights of all other points and the reference point, wherein any one point from a certain central skeleton point and an expanded sampling point is the reference point;
and the height standard deviation is the standard deviation of the difference value between the height value of a certain central framework point and the extended sampling point and the height value of the reference point.
For convenience of subsequent calculation, during teaching, the smallest horizontal coordinate value and the smallest vertical coordinate value in the plane coordinates of each central skeleton point are respectively determined in the smallest detection frame, and the smallest horizontal coordinate value and the smallest vertical coordinate value are respectively subtracted from the horizontal coordinate value and the vertical coordinate value of each central skeleton point and are recorded as the plane coordinates of each central skeleton point.
Further, the method for determining the position of the central skeleton point on the welding seam/adhesive tape in the evaluation area by teaching the plane coordinates of the central skeleton point on the welding seam/adhesive tape in the minimum detection frame in the step 2) comprises the following steps: points at the same positions as the central skeleton point appearing within the minimum detection frame are marked within an evaluation area as large as the minimum detection frame.
The method does not need to adjust the scanning track of the structured light sensor so as to ensure that the emergent light plane of the structured light sensor is always vertical to the extension direction of the adhesive tape/welding seam; the sensor scans arc-shaped welding seams/adhesive tapes along the existing linear track, and the arc-shaped appearance point cloud of the measured object is directly converted into a linear appearance point cloud after being acquired so as to be compatible with the existing processing method of the linear appearance point cloud; the method has the characteristics of high real-time performance, good compatibility and simple and easily-realized calculation process.
In addition, the method reduces the complexity of the robot hand-eye calibration process, the robot track teaching process is simple, the consumed time is short, and the working efficiency is improved; the problem that the robot cannot adjust a proper track is solved, all types of arc-shaped welding seams/rubber strips can be effectively detected, and the universality of a three-dimensional visual detection algorithm is improved.
Drawings
FIG. 1 is a schematic diagram of a visual inspection system for use in the present invention;
FIG. 2 is a schematic plan view of a weld trace collection;
FIG. 3 is a schematic view of an arc shaped topography point cloud (arc welding) in an embodiment;
fig. 4 is a schematic diagram of a point cloud of a linear topography obtained after conversion in the specific embodiment.
Detailed Description
The technical solution of the present invention is described in detail below with reference to the accompanying drawings and the detailed description.
The visual detection method of the arc-shaped welding seam and the adhesive tape comprises two steps, firstly, a standard image to be detected needs to be taught, and then the same image can be detected:
the teaching process comprises the following steps:
firstly, a manually controlled robot 2 drives a structured light sensor 1 to scan an arc-shaped welding seam/adhesive tape 3 along a straight track to obtain a point cloud image to be taught;
marking central skeleton points on the teaching point cloud image along the length direction of the welding seam/adhesive tape at the central line of the teaching point cloud image, and generating a plurality of central skeleton points between two adjacent central skeleton points by a step length A; acquiring a plane coordinate and a height value of each central skeleton point;
respectively taking the central framework point as a center, and expanding towards two sides at equal intervals according to equal step length in a direction perpendicular to a connecting line of two adjacent central framework points to obtain the height value of the corresponding point, wherein the total expanded width of the two sides is the width of a welding seam/adhesive tape, and the expanded points are marked as sampling points to obtain the height value of each sampling point;
marking the minimum area containing all welding seams/adhesive tapes and sampling points on the teaching point cloud image as a minimum detection frame;
calculating the average height difference of each central skeleton point and the expanded sampling points in the minimum detection frame and the height standard difference of each central skeleton point and the expanded sampling points;
the height difference mean value is the mean value of the difference values of the heights of all other points and the reference point, wherein any one point from a certain central skeleton point and an expanded sampling point is the reference point;
the height standard deviation is the standard deviation of the difference value between the height value of a certain central framework point and the extended sampling point and the height value of the reference point.
For convenience of subsequent calculation, during teaching, the smallest horizontal coordinate value and the smallest vertical coordinate value in the plane coordinates of each central skeleton point are respectively determined in the smallest detection frame, and the smallest horizontal coordinate value and the smallest vertical coordinate value are respectively subtracted from the horizontal coordinate value and the vertical coordinate value of each central skeleton point and are recorded as the plane coordinates of each central skeleton point.
Secondly, in the testing process, the robot 2 drives the structured light sensor 1 to scan the arc-shaped welding seam/adhesive tape 3 to be tested along a linear track to obtain arc-shaped appearance point cloud of the tested object, and the arc-shaped appearance point cloud is converted into the linear appearance point cloud by the following steps:
1) determining an interested area of the point cloud image to be evaluated, moving a selection frame in the interested area based on the minimum detection frame size given by teaching to select an area most similar to the height information of the welding seam/adhesive tape in the point cloud image taught, and recording the area as an evaluation area; the minimum detection frame is a minimum area containing all welding seams/adhesive tapes on the teaching point cloud image;
when the evaluation area is determined, the S value corresponding to each selection frame can be obtained, and the selection frame corresponding to the minimum S value is taken as an area most similar to the height information of the welding seam/adhesive tape in the teaching point cloud image;
p is 1,2 … … K, K represents the total number of central skeleton points;
g(p)the height difference mean value of the pth central skeleton point in the selected frame and the sampling point expanded according to the pth central skeleton point is obtained;
h(p)the height standard deviation of the p-th central skeleton point in the selection frame and the sampling point expanded according to the p-th central skeleton point is selected;
g(p)the height difference mean value of the p-th central skeleton point in the minimum detection frame on the teaching point cloud image and the sampling point expanded by the p-th central skeleton point is obtained;
h(p)the height standard deviation of the p-th central skeleton point in the minimum detection frame on the teaching point cloud image and the sampling point expanded by the p-th central skeleton point is calculated;
w1、w2weight, w, representing mean height difference, height standard deviation, respectively1+w2=1;
The height difference mean value is the mean value of the difference values of the heights of all other points and the reference point, wherein any point from the p-th central skeleton point and the extended sampling point is the reference point;
the height standard deviation is the standard deviation of the difference value between the height value of the p-th central skeleton point and the extended sampling point and the height value of the reference point;
the method is only a method for determining the position of the welding seam/adhesive tape through the similarity between the height information of each point in the point cloud image and the height information in the standard image, and other methods can be adopted in actual operation;
2) determining the position of a central skeleton point on a welding seam/adhesive tape in an evaluation area according to the plane coordinates of the central skeleton point on the welding seam/adhesive tape in the minimum detection frame given by teaching, specifically, marking the point at the same position of the central skeleton point in the minimum detection area as the size of the evaluation area is the same as that of the minimum detection area, and considering the point as the position of the central skeleton point; respectively taking a central framework point as a center, and extending towards two sides at equal intervals according to equal step length in a direction perpendicular to a connecting line of two adjacent central framework points to obtain the height value of the corresponding point, wherein the total extended width of the two sides is 130-250% of the width of a welding seam/rubber strip obtained by teaching, and the extended points are marked as sampling points;
the central skeleton point comprises a point manually marked at the position of the central line of the welding seam/adhesive tape during teaching and a point with a step length A sequentially different between two manually marked points;
3) giving out a plane coordinate value corresponding to the height value of each sampling point according to the following rule;
the abscissa of the plane coordinate value is the offset between the sampling point and the corresponding central skeleton point; determining the positive and negative offset according to the relative position of the offset and the central skeleton point; one side is positive and the other side is negative;
the ordinate of the plane coordinate value is the distance between the central skeleton point corresponding to the sampling point and the first central skeleton point; the distance is obtained by moving along the direction of the adhesive tape;
recording other central skeleton points except the first central skeleton point as skeleton points I, wherein the plane coordinate values of all the skeleton points I are (0, the distance between the skeleton point I and the first central skeleton point);
and all the corresponding height values and plane values and the first central skeleton point form a straight line shape point cloud.
The method does not need to adjust the scanning track of the structured light sensor so as to ensure that the emergent light plane of the structured light sensor is always vertical to the extension direction of the adhesive tape/welding seam; the sensor scans arc-shaped welding seams/adhesive tapes along the existing linear track, and the arc-shaped appearance point cloud of the measured object is directly converted into a linear appearance point cloud after being acquired so as to be compatible with the existing processing method of the linear appearance point cloud; the method has the characteristics of high real-time performance, good compatibility and simple and easily-realized calculation process.
In addition, the method reduces the complexity of the robot hand-eye calibration process, the robot track teaching process is simple, the consumed time is short, and the working efficiency is improved; the problem that the robot cannot adjust a proper track is solved, all types of arc-shaped welding seams/rubber strips can be effectively detected, and the universality of a three-dimensional visual detection algorithm is improved.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. The foregoing description is not intended to be exhaustive or to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable others skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications thereof. It is intended that the scope of the invention be defined by the following claims and their equivalents.
Claims (5)
1. A visual detection method for arc-shaped welding seams and adhesive tapes is characterized in that a robot drives a structural optical sensor to scan the arc-shaped welding seams/adhesive tapes along a linear track to obtain arc-shaped appearance point clouds of a detected object, and the arc-shaped appearance point clouds are converted into linear appearance point clouds by the following steps:
1) determining an interested area of the point cloud image to be evaluated, moving a selection frame in the interested area based on the minimum detection frame size given by teaching to select an area most similar to the height information of the welding seam/adhesive tape in the point cloud image taught, and recording the area as an evaluation area; the minimum detection frame is a minimum area containing all welding seams/adhesive tapes on the teaching point cloud image;
2) determining the position of a central skeleton point on a welding seam/adhesive tape in an evaluation area by using a plane coordinate of the central skeleton point on the welding seam/adhesive tape in a minimum detection frame given by teaching, respectively taking the central skeleton point as a center, and extending towards two sides at equal intervals according to equal step length in a direction perpendicular to a connecting line of two adjacent central skeleton points to obtain the height value of the corresponding point, wherein the total width of the extension of the two sides is 130-250% of the width of the welding seam/adhesive tape obtained by teaching, and the extended point is marked as a sampling point;
the central skeleton point comprises a point manually marked at the position of the central line of the welding seam/adhesive tape during teaching and a point sequentially different from the two manually marked points by a step length A;
3) giving out a plane coordinate value corresponding to the height value of each sampling point according to the following rule;
the abscissa of the plane coordinate value is the offset of the sampling point compared with the corresponding central skeleton point;
the ordinate of the plane coordinate value is the distance between the central skeleton point corresponding to the sampling point and the first central skeleton point;
recording other central skeleton points except the first central skeleton point as skeleton points I, wherein the plane coordinate values of all the skeleton points I are (0, the distance between the skeleton point I and the first central skeleton point);
and all the corresponding height values and plane values and the first central skeleton point form a straight line shape point cloud.
2. The visual inspection method for arc-shaped welding seams and rubber strips as claimed in claim 1, characterized in that: step 1) the method for judging the area most similar to the height information of the welding seam/adhesive tape in the teaching point cloud image comprises the following steps: obtaining S values corresponding to all the selection frames, and taking the selection frame corresponding to the minimum S value as an area most similar to the height information of the welding seam/adhesive tape in the teaching point cloud image;
p is 1,2 … … K, K represents the total number of central skeleton points;
g(p)the height difference mean value of the pth central skeleton point in the selected frame and the sampling point expanded according to the pth central skeleton point is obtained;
h(p)the height standard deviation of the p-th central skeleton point in the selection frame and the sampling point expanded according to the p-th central skeleton point is selected;
g(p)the height difference mean value of the p-th central skeleton point in the minimum detection frame on the teaching point cloud image and the sampling point expanded by the p-th central skeleton point is obtained;
h(p)the height standard deviation of the p-th central skeleton point in the minimum detection frame on the teaching point cloud image and the sampling point expanded by the p-th central skeleton point is calculated;
w1、w2weight, w, representing mean height difference, height standard deviation, respectively1+w2=1;
The height difference average value is the average value of the difference values of the heights of all other points and the reference point, wherein any point from the p-th central skeleton point and the extended sampling point is the reference point;
and the height standard deviation is the standard deviation of the difference value between the height value of the p-th central skeleton point and the extended sampling point and the height value of the reference point.
3. The visual inspection method for arc-shaped welding seams and rubber strips as claimed in claim 1, characterized in that: the teaching process comprises the following steps:
firstly, manually controlling a robot to drive a structured light sensor to scan arc-shaped welding seams/adhesive tapes along a straight track to obtain a point cloud image to be taught;
marking central skeleton points on the teaching point cloud image along the length direction of the welding seam/adhesive tape at the central line of the teaching point cloud image, and generating a plurality of central skeleton points between two adjacent central skeleton points by a step length A; acquiring a plane coordinate and a height value of each central skeleton point;
respectively taking the central framework point as a center, and expanding towards two sides at equal intervals according to equal step length in a direction perpendicular to a connecting line of two adjacent central framework points to obtain the height value of the corresponding point, wherein the total expanded width of the two sides is the width of a welding seam/adhesive tape, and the expanded points are marked as sampling points to obtain the height value of each sampling point;
marking the minimum area containing all welding seams/adhesive tapes and sampling points on the teaching point cloud image as a minimum detection frame;
calculating the average height difference of each central skeleton point and the expanded sampling points in the minimum detection frame and the height standard difference of each central skeleton point and the expanded sampling points;
the height difference mean value is the mean value of the difference values of the heights of all other points and the reference point, wherein any one point from a certain central skeleton point and an expanded sampling point is the reference point;
and the height standard deviation is the standard deviation of the difference value between the height value of a certain central framework point and the extended sampling point and the height value of the reference point.
4. The visual inspection method for the arc-shaped welding seam and the rubber strip as claimed in claim 3, characterized in that: during teaching, the minimum horizontal coordinate value and the minimum vertical coordinate value in the plane coordinates of each central skeleton point are respectively determined in the minimum detection frame, and the minimum horizontal coordinate value and the minimum vertical coordinate value are respectively subtracted from the horizontal coordinate value and the minimum vertical coordinate value of each central skeleton point and are recorded as the plane coordinates of each central skeleton point.
5. The visual inspection method for arc-shaped welding seams and rubber strips as claimed in claim 1, characterized in that: the method for determining the position of the central skeleton point on the welding seam/adhesive tape in the evaluation area by using the plane coordinates of the central skeleton point on the welding seam/adhesive tape in the minimum detection frame given by teaching in the step 2) comprises the following steps: points at the same positions as the central skeleton point appearing within the minimum detection frame are marked within an evaluation area as large as the minimum detection frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110182543.XA CN112975907B (en) | 2021-02-08 | 2021-02-08 | Visual detection method for arc-shaped welding seam and adhesive tape |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110182543.XA CN112975907B (en) | 2021-02-08 | 2021-02-08 | Visual detection method for arc-shaped welding seam and adhesive tape |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112975907A CN112975907A (en) | 2021-06-18 |
CN112975907B true CN112975907B (en) | 2022-04-01 |
Family
ID=76393326
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110182543.XA Active CN112975907B (en) | 2021-02-08 | 2021-02-08 | Visual detection method for arc-shaped welding seam and adhesive tape |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112975907B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113686867A (en) * | 2021-07-15 | 2021-11-23 | 昆山丘钛微电子科技股份有限公司 | Dispensing quality detection method and device, medium and camera focusing machine |
CN114120051B (en) * | 2021-11-11 | 2024-06-04 | 易思维(杭州)科技股份有限公司 | Method for screening edge points of adhesive tapes |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105798432A (en) * | 2016-05-27 | 2016-07-27 | 天津智通机器人有限公司 | offline tracking method of curve welding line welded by arc welding robot |
CN107895372A (en) * | 2017-11-14 | 2018-04-10 | 易思维(天津)科技有限公司 | A kind of adhesive tape skeleton line automatic teaching method and system for robot coating detection |
CN110068274A (en) * | 2019-05-29 | 2019-07-30 | 易思维(杭州)科技有限公司 | Gluing sensor adhesive tape detects teaching method |
CN110111424A (en) * | 2019-05-07 | 2019-08-09 | 易思维(杭州)科技有限公司 | The three-dimensional rebuilding method of arc-shaped object based on line-structured light measurement |
CN110189316A (en) * | 2019-05-29 | 2019-08-30 | 易思维(杭州)科技有限公司 | A kind of adhesive tape detection automatic teaching method |
CN112157396A (en) * | 2020-09-21 | 2021-01-01 | 芜湖元正模具机械有限公司 | Welding device for pipe fitting |
-
2021
- 2021-02-08 CN CN202110182543.XA patent/CN112975907B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105798432A (en) * | 2016-05-27 | 2016-07-27 | 天津智通机器人有限公司 | offline tracking method of curve welding line welded by arc welding robot |
CN107895372A (en) * | 2017-11-14 | 2018-04-10 | 易思维(天津)科技有限公司 | A kind of adhesive tape skeleton line automatic teaching method and system for robot coating detection |
CN110111424A (en) * | 2019-05-07 | 2019-08-09 | 易思维(杭州)科技有限公司 | The three-dimensional rebuilding method of arc-shaped object based on line-structured light measurement |
CN110068274A (en) * | 2019-05-29 | 2019-07-30 | 易思维(杭州)科技有限公司 | Gluing sensor adhesive tape detects teaching method |
CN110189316A (en) * | 2019-05-29 | 2019-08-30 | 易思维(杭州)科技有限公司 | A kind of adhesive tape detection automatic teaching method |
CN112157396A (en) * | 2020-09-21 | 2021-01-01 | 芜湖元正模具机械有限公司 | Welding device for pipe fitting |
Also Published As
Publication number | Publication date |
---|---|
CN112975907A (en) | 2021-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111505606B (en) | Method and device for calibrating relative pose of multi-camera and laser radar system | |
CN112975907B (en) | Visual detection method for arc-shaped welding seam and adhesive tape | |
CN107798330A (en) | A kind of weld image characteristics information extraction method | |
CN110111424B (en) | Three-dimensional reconstruction method of arc-shaped object based on line structured light measurement | |
CN102279190B (en) | Image detection method for weld seam surface defects of laser welded plates of unequal thickness | |
CN111604909A (en) | Visual system of four-axis industrial stacking robot | |
CN110906863B (en) | Hand-eye calibration system and calibration method for line-structured light sensor | |
CN111815717B (en) | Multi-sensor fusion external parameter combination semi-autonomous calibration method | |
CN110503638B (en) | Spiral adhesive quality online detection method | |
CN112529858A (en) | Welding seam image processing method based on machine vision | |
US11504846B2 (en) | Robot teaching system based on image segmentation and surface electromyography and robot teaching method thereof | |
CN111702054B (en) | In-situ shape-adjusting detection system and method for progressive forming of curved plate | |
CN112950633B (en) | Aluminum alloy weld joint surface defect detection method based on line structured light | |
CN110146017B (en) | Industrial robot repeated positioning precision measuring method | |
CN113251926B (en) | Method and device for measuring size of irregular object | |
CN109978940A (en) | A kind of SAB air bag size vision measuring method | |
CN114714355A (en) | Embedded vision tracking control system of autonomous mobile welding robot | |
CN111570974B (en) | Welding deviation measuring method and device based on synchronous drawing and automatic welding system | |
CN111523611A (en) | Gluing detection method | |
CN110530273A (en) | Gluing information detecting method based on structural light measurement | |
CN113781434A (en) | Defect detection method and device, intelligent terminal and computer readable storage medium | |
CN114434036B (en) | Three-dimensional vision system for gantry robot welding of large ship structural member and operation method | |
CN113601501B (en) | Flexible operation method and device for robot and robot | |
CN116465335A (en) | Automatic thickness measurement method and system based on point cloud matching | |
CN112975222B (en) | Welding gun tail end pose identification method based on multi-line structured light welding seam tracking sensor |
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 | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |