CN114509023A - Magnetic nail identification and positioning device, coordinate robot and magnetic nail identification and positioning method - Google Patents
Magnetic nail identification and positioning device, coordinate robot and magnetic nail identification and positioning method Download PDFInfo
- Publication number
- CN114509023A CN114509023A CN202210151739.7A CN202210151739A CN114509023A CN 114509023 A CN114509023 A CN 114509023A CN 202210151739 A CN202210151739 A CN 202210151739A CN 114509023 A CN114509023 A CN 114509023A
- Authority
- CN
- China
- Prior art keywords
- mold
- laser
- magnetic
- point cloud
- magnetic nail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000010586 diagram Methods 0.000 claims description 7
- 238000013499 data model Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000011178 precast concrete Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/25—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/25—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object
- G01B11/2545—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object with one projection direction and several detection directions, e.g. stereo
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of robots, in particular to a magnetic nail identification and positioning device, a coordinate robot and a magnetic nail identification and positioning method. The magnetic nail identification and positioning device comprises: the laser is suitable for being arranged on the Z-axis truss of the coordinate robot and used for emitting laser lines to the die table; the 2D camera is suitable for being arranged on the Z-axis truss and is used for shooting the laser line on the die table; wherein, the 2D camera can shoot the complete laser line emitted by the laser. According to the method, the 3D point cloud data of the surface of the mold table can be obtained through the 2D camera and the laser generator, the 3D camera is not needed, the cost is low, and the recognition success rate is high.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a magnetic nail identification and positioning device, a coordinate robot and a magnetic nail identification and positioning method.
Background
The cartesian robot is widely applied to various industrial fields as an automatic robot with a simple structure, and in the assembly type building industry, the coordinate robot is used for replacing manual work to place and remove side forms of Precast Concrete (PC) members, wherein when the robot automatically retrieves a mold, the robot needs to identify and position the mold, and the more difficult is to automatically remove magnetic nails firstly, so that the positions of the magnetic nails on the mold need to be accurately positioned.
The size of the whole mold table is 9m multiplied by 4m, magnetic nails of all molds on the mold table need to be identified and positioned, the diameter of each magnetic nail is 50mm, the height of each magnetic nail is 25mm, the magnetic nail is very small relative to the mold table, when a tiny object is accurately identified and positioned in a large-view scene, a linear scanning 3D camera with high image precision requirement needs to be adopted for single scanning to obtain a three-dimensional image of the whole mold table, then the position of the magnetic nail is analyzed, and the magnetic nail positioning function can be quickly realized by using the linear scanning 3D camera, however, the cost of the 3D camera is too high, and a magnetic nail identification and positioning device and method with lower cost are urgently needed.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the defect of high cost of the 3D camera in the prior art, so as to provide a magnetic nail identification and positioning device, a coordinate robot and a magnetic nail identification and positioning method.
In order to solve the above problems, the present invention provides a magnetic nail identification and positioning device, comprising: the laser is suitable for being arranged on the Z-axis truss of the coordinate robot and used for emitting laser lines to the die table; the 2D camera is suitable for being arranged on the Z-axis truss and is used for shooting the laser line on the die table; wherein, the 2D camera can shoot the complete laser line emitted by the laser.
Optionally, the 2D camera and the laser are located on the same side of the Z-axis truss.
Optionally, the laser line emitted by the laser extends in the Y direction of the coordinate robot.
Alternatively, the 2D camera and the laser are arranged along the X direction of the coordinate robot.
The present invention also provides a coordinate robot, comprising: the magnetic nail identification and positioning device is provided.
The invention also provides a magnetic nail identification and positioning method, which comprises the following steps: controlling the Z-axis truss to move along a preset direction, controlling the laser to emit a laser line to the mold table, and controlling the 2D camera to shoot the laser line so as to obtain 3D point cloud data on the surface of the mold table; processing the 3D point cloud data to obtain a two-dimensional image outline of the mold on the mold table; and calculating the coordinates of the two magnetic nails on the mold through the two-dimensional image profile.
Optionally, the step of processing the 3D point cloud data includes: analyzing the 3D point cloud data to construct a three-dimensional data model; intercepting and projecting 3D point cloud data of the height of the mold to obtain a two-dimensional plane diagram; and removing the noise data in the two-dimensional plane graph to obtain the two-dimensional image outline of the mold.
Optionally, the step of analyzing the 3D point cloud data and the step of intercepting and projecting the 3D point cloud data at the height of the mold further include: and removing redundant point cloud noise in the 3D point cloud data.
Optionally, the step of obtaining the X coordinate and the Y coordinate of the two magnetic nails on the mold through two-dimensional image contour calculation includes: matching and positioning are carried out through the two-dimensional image outline and an image template generated by a mold drawing so as to obtain the coordinate of the center of each side die in the mold, the length of each side die, the included angle between each side die and an X axis and the distance from the magnetic nail to one end, close to the magnetic nail, of each side die; and calculating the coordinates of the centers of the two magnetic nails on the side die through the coordinates of the center of the side die, the length of the side die, the included angle between the side die and the X axis and the distance from the magnetic nail to one end of the side die close to the magnetic nail.
Optionally, the coordinates of the two magnetic nails on the side die are respectively (X)1,Y1) And (X)1,Y1) Wherein X is1＝X0-(L/2-H)×cosβ，Y1＝Y0+(L/2-H)×sinβ，X2＝X0+(L/2-H)×cosβ，Y2＝Y0- (L/2-H). times.sin beta., the coordinate of the center of the side mold is (X)0,Y0) L is the length of the side die, beta is the included angle between the side die and the X axis, and H is the distance from the magnetic nail to one end of the side die close to the magnetic nail.
The invention has the following advantages:
the laser emits laser lines to the die table, a die is arranged on the die table, one laser line is projected to the surface of an object, the height of the surface of the object changes, the shot laser line can be correspondingly bent, the three-dimensional outline of the surface of the object can be calculated according to the deformation of the laser line, then the laser line emitted by the laser on the surface of the die table is shot through the 2D camera, a series of pixel coordinates and depth coordinates of the surface of the die table can be obtained, then the Z-axis truss moves at a constant speed in the preset direction to further obtain complete 3D point cloud data on the die table, the 3D point cloud data on the surface of the die table can be obtained through the 2D camera and the laser generator, the 3D camera does not need to be used, the cost is low, and the identification success rate is high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 shows a perspective view of a coordinate robot according to an embodiment of the present invention;
fig. 2 shows a simple schematic diagram of the coordinate robot of fig. 1 with the fixing frame, the laser, and the 2D camera cooperating with the mold table and the side mold;
FIG. 3 shows a schematic diagram of the laser, 2D camera and side mode of FIG. 2 in cooperation;
FIG. 4 is a partial schematic view of a 2D camera of the magnetic pin identification and positioning method of the present invention capturing a frame of scanned image;
FIG. 5 shows a 3D point cloud image after the 2D camera of the magnetic nail identification and positioning method of the present invention scans;
FIG. 6 shows the segmentation and projection of a 3D point cloud image to a resulting two-dimensional plane map of the magnetic pin identification and localization method of the present invention;
FIG. 7 is a schematic diagram of matching an image template generated by using a die drawing with a two-dimensional image contour according to the magnetic nail identification and positioning method of the present invention;
fig. 8 shows a schematic diagram of the principle of calculating the coordinates of the center of the magnetic nail according to the magnetic nail identification and positioning method of the invention.
Description of reference numerals:
10. a laser; 11. a laser line; 20. a 2D camera; 21. a lens; 30. a Z-axis truss; 40. a column; 50. an X-axis truss; 60. a Y-axis truss; 70. the R shaft rotates the gripper; 80. a fixed mount; 90. a control cabinet; 100. a mould table; 110. and (5) side molding.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, 2 and 4, the magnetic pin identification and positioning device of the present embodiment includes: a laser 10 and a 2D camera 20, the laser 10 being adapted to be disposed on a Z-axis truss 30 of the coordinate robot and to emit a laser line to the mold table 100; the 2D camera 20 is adapted to be disposed on the Z-axis truss 30 and to photograph the laser line on the mold table 100; wherein the 2D camera 20 can shoot the complete laser line 11 emitted by the laser 10.
By applying the magnetic nail identification and positioning device of the embodiment, the laser 10 emits a laser line to the mold 100, as the mold is arranged on the mold 100, one laser line is projected to the surface of an object, as the height of the surface of the object changes, the shot laser line 11 can be correspondingly bent, the three-dimensional outline of the surface of the object can be calculated according to the deformation of the laser line, then the laser line 11 emitted by the laser 10 on the surface of the mold is shot through the 2D camera 20, a series of pixel coordinates and depth coordinates of the surface of the mold can be obtained, then the complete 3D point cloud data on the mold can be further obtained by utilizing the uniform motion of the Z-axis truss 30 in the preset direction, the 3D point cloud data on the surface of the mold can be obtained through the 2D camera 20 and the laser generator, the 3D camera does not need to be used, the cost is low, and the identification success rate is high.
In this embodiment, the 2D camera 20 and the laser 10 are located on the same side of the Z-axis truss 30, which facilitates the 2D camera 20 to shoot the laser line emitted by the laser 10 on the surface of the mold table. Preferably, the geometric center line of the 2D camera 20 and the geometric center line of the laser 10 form an included angle, so that 3D point cloud data can be obtained conveniently. The 2D camera 20 includes a body and a lens 21, and the lens 21 is mounted on the body.
In the present embodiment, as shown in fig. 2 and 3, the geometric center line of the laser 10 is arranged in the vertical direction, which facilitates the installation of the laser 10 and also facilitates the calculation of the coordinates of the magnetic nail.
In the present embodiment, the laser line emitted by the laser 10 extends in the Y direction of the coordinate robot. Wherein, the length direction of the die table 100 is the X direction, the width direction of the die table 100 is the Y direction, the length of the laser line emitted by the laser 10 is short, and the cost is reduced. It will be appreciated that in other embodiments, the laser line emitted by the laser 10 extends in the X-direction, and the uniform motion of the Z-truss 30 in the Y-direction may further result in complete 3D point cloud data on the stage.
In the present embodiment, as shown in fig. 2 and 3, the 2D camera 20 and the laser 10 are arranged along the X direction of the coordinate robot, facilitating the 2D camera 20 to photograph the laser line emitted by the laser 10.
The present invention also provides a coordinate robot, comprising: the magnetic nail identification and positioning device is provided.
In this embodiment, as shown in fig. 1 to 3, the coordinate robot further includes a column 40, two X-axis trusses 50, a Y-axis truss 60, a Z-axis truss 30, and an R-axis rotary gripper 70, the two X-axis trusses 50 are oppositely disposed and disposed on the column 40, the Y-axis truss 60 is movably connected to the two X-axis trusses 50, the Z-axis truss 30 is connected to the Y-axis truss 60 in a vertically liftable manner, and the R-axis rotary gripper 70 is rotatably connected to the Z-axis truss 30.
In this embodiment, the coordinate robot further includes a fixing frame 80, the fixing frame 80 is fixed on the Z-axis truss 30, the laser 10 and the 2D camera 20 are fixed on the fixing frame 80, and the laser 10 and the 2D camera 20 are fixed by the fixing frame 80, so that the fixing manner is simple and convenient.
In this embodiment, the coordinate robot still includes the vision device, the vision device includes 2D camera 20 and laser instrument 10, laser instrument 10 is the line laser instrument, shoot the laser line on the mould platform surface that the line laser instrument launches through 2D camera 20, can obtain a series of pixel coordinates and the depth coordinate on mould platform surface, the Z axle truss of recycling coordinate robot can further obtain complete mould platform 3D surface profile at the uniform velocity motion in the X direction, can realize whole mould platform low-cost 3D point cloud data acquisition, can utilize the CAD drawing of known mould to generate the image template that is used for the matching simultaneously, once only realize mould discernment and location on the whole mould platform.
In the present embodiment, the coordinate robot further includes a control cabinet 90, and the control cabinet 90 is used to control the line laser 10, the 2D camera 20, the Y-axis truss 60, the Z-axis truss 30, and the like.
The invention also provides a magnetic nail identification and positioning method, as shown in fig. 2 to 4, comprising the following steps:
controlling the Z-axis truss 30 to move along a preset direction, controlling the laser 10 to emit a laser line to the mold table, and controlling the 2D camera 20 to shoot the laser line so as to obtain 3D point cloud data on the surface of the mold table, wherein the preset direction is an X direction;
processing the 3D point cloud data to obtain a two-dimensional image outline of the mold on the mold table;
and calculating the coordinates of the two magnetic nails on the mold through the two-dimensional image profile.
By applying the magnetic nail identification and positioning method of the embodiment, the laser 10 emits a laser line to the mold, because the mold is arranged on the mold, one laser line is projected on the surface of an object, because the height of the surface of the object changes, the shot laser line can be correspondingly bent, the three-dimensional outline of the surface of the object can be calculated according to the deformation of the laser line, then the laser line emitted by the laser 10 on the surface of the mold is shot by the 2D camera 20, a series of pixel coordinates and depth coordinates of the surface of the mold can be obtained, then the 3D point cloud data on the mold can be further obtained by utilizing the uniform motion of the Z-axis truss 30 in the preset direction, the 3D point cloud data on the surface of the mold can be obtained by the 2D camera 20 and the laser generator, the 3D point cloud data on the surface of the mold can be obtained without using a 3D camera, the cost is low, the identification success rate is high, and the magnetic nail identification and positioning method adopts a geometric positioning method of fixing magnetic nails by using the mold, the problems of unobvious magnetic nail data characteristics and difficulty in positioning are solved, the magnetic nail can be positioned at low cost, and then the nail can be accurately pulled out and the side die can be detached.
In this embodiment, the laser 10 projects a laser line onto the surface of the object, and the photographed laser line is correspondingly curved due to the height change of the surface of the object, so that the three-dimensional contour of the surface of the object can be calculated according to the deformation of the line. As shown in fig. 3, an included angle between the incident light AO and the reflected light OC is θ, an included angle between the reflected light OC and the photosensitive surface BC of the 2D camera 20 is α, a plane where the point O is located is assumed as a reference plane, a plane where the point a is located is assumed as an object surface, perpendicular lines from a and B to the reflected light OC are respectively made to obtain points E and D, and according to the principle of similarity of triangles, the method can obtain:
wherein BC is image motion and AO1Is the object distance of the image, O1C is the imaging image distance, α can be mounted to 90 °, the above equation can be simplified to:
the Y-axis position information along the laser line can be calculated through the image information shot by the 2D camera 20, the X-axis information can be obtained through the position data moved by the Z-axis truss along the X direction, the relative pose between the 2D camera and the plane where the laser line is located is calibrated, the relative motion between the target object and the imaging system is calibrated, the 3D coordinates of all points on the surface can be obtained, and then the 3D point cloud data is obtained.
In this embodiment, the preset direction is the X direction, the laser line extends along the Y direction, and the Z-axis truss 30 moves at a constant speed in the X direction to further obtain the complete 3D point cloud data on the mold table. It is understood that in other embodiments, the preset direction is the Y direction, the laser line emitted by the laser 10 extends along the X direction, and the uniform motion of the Z-axis truss 30 in the Y direction can further obtain the complete 3D point cloud data on the mold table.
In this embodiment, the step of processing the 3D point cloud data includes: analyzing the 3D point cloud data to construct a three-dimensional data model; intercepting and projecting 3D point cloud data of the height of the mold to obtain a two-dimensional plane diagram; and removing the noise data in the two-dimensional plane graph to obtain the two-dimensional image outline of the mold. The two-dimensional image profile of the die obtained through the steps is more accurate, and the positioning precision is high.
In this embodiment, the steps of analyzing the 3D point cloud data and intercepting and projecting the 3D point cloud data at the height of the mold further include: and removing redundant point cloud noise in the 3D point cloud data. Non-side mode noise data can be filtered by removing the noise data twice, and the identification and positioning accuracy is improved. Of course, no step may be provided to remove the redundant point cloud noise in the 3D point cloud data.
Preferably, in the step of removing the redundant point cloud noise in the 3D point cloud data, the redundant point cloud noise in the 3D point cloud data is removed by a clustering algorithm in combination with a 3D point cloud area threshold method. Of course, other algorithms may be used to remove the point cloud noise, but are not limited thereto.
In this embodiment, as shown in fig. 2 and 8, the step of obtaining the X-coordinate and the Y-coordinate of the two magnetic pins on the mold by two-dimensional image contour calculation includes: matching and positioning are carried out through the two-dimensional image outline and an image template generated by a mold drawing so as to obtain the coordinates of the center of each side die 110 in the mold, the length of each side die 110, the included angle between each side die 110 and the X axis and the distance from the magnetic nail to one end, close to the magnetic nail, of each side die 110; the coordinates of the centers of the two magnetic nails on the side die 110 are calculated through the coordinates of the center of the side die 110, the length of the side die 110, the included angle between the side die 110 and the X axis and the distance from the magnetic nail to one end of the side die 110 close to the magnetic nail. The mold drawing is used for generating the image template and the image contour calculated by the 3D point cloud data is matched to realize the identification and the positioning of the mold on the whole mold table, the on-site collection of the mold image is replaced, the on-site collection of the image is not needed, and the method is more accurate and high in efficiency. It is understood that in other embodiments, the geometric characteristics of the circumscribed rectangle of the image may also be directly calculated after the clustering algorithm is combined with the 3D point cloud area threshold method to remove the redundant point cloud noise in the 3D point cloud data.
In the present embodiment, the coordinates of the two magnetic nails on the side mold 110 are (X) respectively1,Y1) And (X)1,Y1) Wherein X is1＝X0-(L/2-H)×cosβ，Y1＝Y0+(L/2-H)×sinβ，X2＝X0+(L/2-H)×cosβ，Y2＝Y0- (L/2-H). times.sin beta., the coordinate of the center of the side mold 110 is (X)0,Y0) L is the length of the side die, beta is the included angle between the side die and the X axis, and H is the distance from the magnetic nail to one end, close to the magnetic nail, of the side die.
In this embodiment, place the mould platform in the coordinate robot, it is a plurality of to place side forms and magnetic nail on the mould platform, after moving R axle rotation tongs to safe height, follow mould platform initiating position and scan at the uniform velocity along the X direction, the laser line that laser emission was on the mould platform can constantly be shot to the 2D camera according to the positional information of coordinate robot system feedback, the 3D point cloud data of whole mould platform finally generates, 3D cloud data includes pixel coordinate and depth coordinate, can realize whole mould platform low cost 3D point cloud data acquisition, wherein, figure 5 is forSide mode 3D point cloud. After 3D point cloud data can be obtained according to a 2D camera, a three-dimensional data model is constructed by analyzing the point cloud data, redundant point cloud noise exists in the 3D point cloud image in the image 5, and partial noise can be removed by combining a clustering algorithm in point cloud data preprocessing with a 3D point cloud area threshold method. The picture shown in fig. 6 is a two-dimensional plane graph obtained by intercepting point cloud data of the height of the mold and performing projection, the image is obtained through two-dimensional image preprocessing, and non-side mode noise data can be filtered out due to the fact that the side mode is placed at a certain height, so that the outline of the two-dimensional image is obtained. As shown in fig. 7, coordinates (X) of the center of the side mold on the mold stage can be obtained by performing image matching positioning on the image template generated by traversing the mold drawings of different side molds and the two-dimensional image profile0,Y0) The length L of the side die, the included angle beta between the side die and the X axis and the distance H from the magnetic nail to one end of the side die close to the magnetic nail pass through a central point (X)0,Y0) The length L of the side die, the included angle beta between the side die and the X axis and the distance H from the magnetic nail to one end of the side die close to the magnetic nail can be calculated to obtain the coordinate (X) of the centers of the two magnetic nails1,Y1) And (X)1,Y1) Wherein X is1＝X0-(L/2-H)×cosβ，Y1＝Y0+(L/2-H)×sinβ，X2＝X0+(L/2-H)×cosβ，Y2＝Y0-(L/2-H)×sinβ。
From the above description, it can be seen that the above-described embodiments of the present invention achieve the following technical effects:
1. projecting a laser line on the surface of an object, wherein the laser line is bent due to the change of the height of the surface of the object, calculating the height of each point on the laser line relative to a reference plane according to the deformation of the line, shooting the laser line by a 2D camera, extracting the laser line in a frame of image through image binarization processing and morphological analysis, scanning a mould table along the X-axis direction to obtain all laser lines on the mould table, calculating the corresponding Z coordinate of the X coordinate and the Y coordinate of the point of each laser line to obtain 3D point cloud data of the whole platform, realizing the large-scene and low-cost 3D point cloud data acquisition of the mould table by using a method of scanning the whole mould table by a separation type laser triangulation method to obtain a surface 3D point cloud coordinate, replacing a binocular vision and 3D structured light imaging mode, and correcting a large visual field error by the aid of a workpiece characteristic method, the magnetic nail positioning can be realized at relatively high cost.
2. The image template generated by the mold CAD drawing and the image outline calculated by the 3D point cloud data are matched, so that the identification and positioning of the whole mold platform mold can be realized, the on-site image acquisition is not needed, the efficiency is high, and the on-site mold image acquisition is replaced by the image template generated by the mold drawing in a ratio of 1:1, so that the accuracy is higher.
3. The magnetic nail is finally positioned by combining image matching, identification and positioning with geometric calculation, the problem that the image characteristics of the magnetic nail are difficult to process directly is solved, positioning in a size-fixed mode is realized, and the magnetic nail positioning precision is improved.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A magnetic nail identification and positioning device is characterized by comprising:
a laser (10) adapted to be disposed on a Z-axis truss (30) of the coordinate robot and for emitting a laser line to the mold table;
a 2D camera (20) adapted to be disposed on the Z-axis truss (30) and to photograph the laser line on the stage;
wherein the 2D camera (20) can shoot the complete laser line emitted by the laser (10).
2. A magnetic pin identification and positioning device according to claim 1, wherein the 2D camera (20) and the laser (10) are located on the same side of the Z-axis truss (30).
3. A magnetic pin identification and positioning device according to claim 2, characterized in that the laser line emitted by the laser (10) extends in the Y-direction of the coordinate robot.
4. A magnetic pin recognition positioning device according to claim 3, characterized in that the 2D camera (20) and the laser (10) are arranged along the X direction of the coordinate robot.
5. A coordinate robot, comprising: a magnetic pin identification and positioning device as claimed in any one of claims 1 to 4.
6. A magnetic nail identification and positioning method is characterized by comprising the following steps:
controlling a Z-axis truss (30) to move along a preset direction, controlling a laser (10) to emit a laser line to a mold table, and controlling a 2D camera (20) to shoot the laser line so as to obtain 3D point cloud data on the surface of the mold table;
processing the 3D point cloud data to obtain a two-dimensional image outline of the mold on the mold table;
and calculating the coordinates of the two magnetic nails on the mold according to the two-dimensional image profile.
7. The magnetic nail identification and positioning method according to claim 6, wherein the step of processing the 3D point cloud data comprises:
analyzing the 3D point cloud data to construct a three-dimensional data model;
intercepting and projecting the 3D point cloud data of the height of the mold to obtain a two-dimensional plane diagram;
and removing the noise data in the two-dimensional plane graph to obtain a two-dimensional image outline of the mold.
8. The magnetic nail identification and positioning method according to claim 7, further comprising, between the step of analyzing the 3D point cloud data and the step of intercepting and projecting the 3D point cloud data at the height of the mold:
and removing redundant point cloud noise in the 3D point cloud data.
9. The magnetic pin identification and positioning method according to claim 6, wherein the step of calculating the X coordinates and the Y coordinates of the two magnetic pins on the mold through the two-dimensional image profile comprises the following steps:
matching and positioning the two-dimensional image outline and an image template generated by a mold drawing to obtain the coordinates of the center of each side die in the mold, the length of each side die, the included angle between each side die and the X axis and the distance from the magnetic nail to one end, close to the magnetic nail, of each side die;
and calculating the coordinates of the centers of the two magnetic nails on the side die according to the coordinates of the center of the side die, the length of the side die, the included angle between the side die and the X axis and the distance from the magnetic nail to one end of the side die close to the magnetic nail.
10. The magnetic nail identification and positioning method according to claim 9, wherein the coordinates of the two magnetic nails on the side mold are respectively (X)1,Y1) And (X)1,Y1) Wherein X is1＝X0-(L/2-H)×cosβ，Y1＝Y0+(L/2-H)×sinβ，X2＝X0+(L/2-H)×cosβ，Y2＝Y0- (L/2-H). times.sin beta. and the coordinate of the center of the side mold is (X)0,Y0) L is the length of the side die, beta is an included angle between the side die and the X axis, and H is the distance from the magnetic nail to one end, close to the magnetic nail, of the side die.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210151739.7A CN114509023B (en) | 2022-02-18 | 2022-02-18 | Magnetic nail identification positioning device, coordinate robot and magnetic nail identification positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210151739.7A CN114509023B (en) | 2022-02-18 | 2022-02-18 | Magnetic nail identification positioning device, coordinate robot and magnetic nail identification positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114509023A true CN114509023A (en) | 2022-05-17 |
| CN114509023B CN114509023B (en) | 2024-03-08 |
Family
ID=81551702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210151739.7A Active CN114509023B (en) | 2022-02-18 | 2022-02-18 | Magnetic nail identification positioning device, coordinate robot and magnetic nail identification positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114509023B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203117114U (en) * | 2013-01-31 | 2013-08-07 | 长安大学 | Precision-adjustable detecting device for notch grooves of cement pavement |
| CN104266587A (en) * | 2014-09-22 | 2015-01-07 | 电子科技大学 | Three-dimensional measurement system and method for obtaining actual 3D texture point cloud data |
| CN105783770A (en) * | 2016-01-22 | 2016-07-20 | 西南科技大学 | Method for measuring ice shaped contour based on line structured light |
| CN106091984A (en) * | 2016-06-06 | 2016-11-09 | 中国人民解放军信息工程大学 | A kind of three dimensional point cloud acquisition methods based on line laser |
| CN111259829A (en) * | 2020-01-19 | 2020-06-09 | 北京小马慧行科技有限公司 | Point cloud data processing method and device, storage medium and processor |
| KR20200116666A (en) * | 2019-04-02 | 2020-10-13 | (주) 엠엔비젼 | The 4-axis body measurement system using a laser scan |
| JP2021025917A (en) * | 2019-08-06 | 2021-02-22 | 株式会社キーエンス | Three-dimensional shape measurement device |
-
2022
- 2022-02-18 CN CN202210151739.7A patent/CN114509023B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203117114U (en) * | 2013-01-31 | 2013-08-07 | 长安大学 | Precision-adjustable detecting device for notch grooves of cement pavement |
| CN104266587A (en) * | 2014-09-22 | 2015-01-07 | 电子科技大学 | Three-dimensional measurement system and method for obtaining actual 3D texture point cloud data |
| CN105783770A (en) * | 2016-01-22 | 2016-07-20 | 西南科技大学 | Method for measuring ice shaped contour based on line structured light |
| CN106091984A (en) * | 2016-06-06 | 2016-11-09 | 中国人民解放军信息工程大学 | A kind of three dimensional point cloud acquisition methods based on line laser |
| KR20200116666A (en) * | 2019-04-02 | 2020-10-13 | (주) 엠엔비젼 | The 4-axis body measurement system using a laser scan |
| JP2021025917A (en) * | 2019-08-06 | 2021-02-22 | 株式会社キーエンス | Three-dimensional shape measurement device |
| CN111259829A (en) * | 2020-01-19 | 2020-06-09 | 北京小马慧行科技有限公司 | Point cloud data processing method and device, storage medium and processor |
Non-Patent Citations (1)
| Title |
|---|
| 周平;王从军;陈鑫;: "计算机单目视觉测量系统", 光电工程, no. 12, 28 December 2005 (2005-12-28), pages 90 - 93 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114509023B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110497187B (en) | Sun flower pattern assembly system based on visual guidance | |
| CN106056587B (en) | Full view line laser structured light three-dimensional imaging caliberating device and method | |
| CN110487213A (en) | Full view line laser structured light three-dimensional image forming apparatus and method based on spatial offset | |
| CN109739239B (en) | Planning method for uninterrupted instrument recognition of inspection robot | |
| CN111121655A (en) | Visual detection method for pose and aperture of coplanar workpiece with equal large hole patterns | |
| CN112518132B (en) | Hub burr removing method and electronic device | |
| JP7174074B2 (en) | Image processing equipment, work robots, substrate inspection equipment and specimen inspection equipment | |
| CN112697112B (en) | Method and device for measuring horizontal plane inclination angle of camera | |
| CN113324478A (en) | Center extraction method of line structured light and three-dimensional measurement method of forge piece | |
| JPH11166818A (en) | Calibrating method and device for three-dimensional shape measuring device | |
| CN112658643B (en) | Connector assembly method | |
| JP5001330B2 (en) | Curved member measurement system and method | |
| EP3975116A1 (en) | Detecting displacements and/or defects in a point cloud using cluster-based cloud-to-cloud comparison | |
| Jiang et al. | A ball-shaped target development and pose estimation strategy for a tracking-based scanning system | |
| CN116560062B (en) | Microscope focusing anti-collision control method | |
| CN114509023B (en) | Magnetic nail identification positioning device, coordinate robot and magnetic nail identification positioning method | |
| JPH06243236A (en) | Setting device for coordinate system correction parameter of visual recognizer | |
| CN113592962B (en) | Batch silicon wafer identification recognition method based on machine vision | |
| CN214212596U (en) | Wheel hub processing equipment | |
| CN109506626A (en) | A kind of measurement method of camera tilt angles | |
| JP2519445B2 (en) | Work line tracking method | |
| JP7365567B2 (en) | Measurement system, measurement device, measurement method and measurement program | |
| CN115222893A (en) | Three-dimensional reconstruction splicing method for large-size components based on structured light measurement | |
| JPH06258028A (en) | Method and system for visually recognizing three dimensional position and attitude | |
| Cheng et al. | New method and system of automatically moving a CMM probe tip into holes with submillimeter diameter and high aspect ratio |
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 |