CN111609801B - Multi-size workpiece thickness measuring method and system based on machine vision - Google Patents
Multi-size workpiece thickness measuring method and system based on machine vision Download PDFInfo
- Publication number
- CN111609801B CN111609801B CN202010481273.8A CN202010481273A CN111609801B CN 111609801 B CN111609801 B CN 111609801B CN 202010481273 A CN202010481273 A CN 202010481273A CN 111609801 B CN111609801 B CN 111609801B
- Authority
- CN
- China
- Prior art keywords
- workpiece
- image
- laser scanner
- laser
- point cloud
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims description 16
- 229910000831 Steel Inorganic materials 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 9
- 239000010959 steel Substances 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 22
- 238000001514 detection method Methods 0.000 abstract description 9
- 238000000691 measurement method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005305 interferometry Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000002366 time-of-flight method Methods 0.000 description 1
- 230000009466 transformation 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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a machine vision-based multi-size workpiece thickness measuring method and system, and belongs to the field of machine vision detection and measurement. A CCD camera and a laser scanner are adopted as image acquisition equipment and are unified under the same world coordinate system. The CCD camera shoots the workpiece image entering the shooting area on the conveying belt, the workpiece image is conveyed to the terminal, the vertex of the minimum external rectangle of the workpiece and the vertex of the minimum external rectangle of the workpiece are calculated, and the terminal judges the position and the area of the workpiece according to the vertex coordinates of the minimum external rectangle. The position information of the workpiece is used for adjusting the position of the scanner, and the area of the workpiece judges the working mode of the camera. And the terminal generates a 3D global profile of the workpiece according to the image information acquired by the laser scanner to obtain the thickness of the workpiece. The method reduces the manual participation, saves the labor cost, can measure the thicknesses of workpieces with different sizes in the same set of measuring system, can measure rigid targets or non-rigid target objects, and improves the automation degree of detection.
Description
Technical Field
The invention belongs to the field of machine vision detection and measurement, and particularly relates to a method and a system for measuring the thickness of a multi-size workpiece based on machine vision.
Background
In modern industrial automation which develops rapidly, the requirements of the detection of the geometric dimension of the workpiece, particularly the measurement of the thickness of the workpiece, on the precision and the efficiency are higher and higher, and the workpieces to be measured have the problems of different dimensions and complex surface texture structure, so that the requirements on the rapidity, the robustness and the automation degree of the measurement method are higher.
Today, three-dimensional dimension measurement techniques for semi-finished or finished workpieces on production lines are mainly classified into contact inspection and non-contact inspection. The contact detection methods mainly include a coordinate measuring machine, a chromatography and the like, and although some methods have high measurement accuracy, the methods are easy to rub and damage the surface of a workpiece. The conventional non-contact measurement mainly includes moire fringe method, interferometry, time-of-flight method, structured light method, etc., but these methods or measurement methods have low efficiency or low accuracy, and the workpiece must be taken off-line during measurement, which is likely to cause scratch and damage to the workpiece when the workpiece is unloaded and loaded, and affect the measurement result and subsequent use. And the method cannot accurately and quickly measure the workpiece with variable sizes. Therefore, a flexible, efficient, accurate and highly automated workpiece thickness detection technology is urgently needed.
Disclosure of Invention
The technical problem is as follows: in order to solve the problems that a traditional workpiece three-dimensional size measuring method is easy to damage workpieces, low in measuring efficiency and measuring precision, and inflexible in measurement in the face of complicated and variable workpiece sizes, the patent provides a multi-size workpiece thickness measuring method and system based on machine vision.
The technical scheme is as follows: the invention discloses a machine vision-based multi-size workpiece thickness measuring method, which comprises the following steps of:
step one, starting a system, executing step two if a workpiece is detected to enter a shooting area of a CCD camera, otherwise, waiting for the system, and judging again after adjusting the placing position of the workpiece;
secondly, when the workpiece enters a shooting area of the CCD camera, the camera shoots a two-dimensional image of the workpiece;
thirdly, the terminal calls a processing module to perform image processing on the shot workpiece image, the edge contour of the workpiece is detected, the minimum circumscribed rectangle of the workpiece is generated according to the detected contour, and coordinates of four vertexes of the circumscribed rectangle are obtained;
the terminal adjusts the position of the laser scanner according to the coordinates of the vertex of the minimum circumscribed rectangle, judges whether the laser scanning area of the first-level laser scanner can cover the whole workpiece or not according to the area of the minimum circumscribed rectangle, if the laser scanning area can cover the whole workpiece, the three-dimensional image of the workpiece can be generated according to the scanned surface image of the workpiece, so that the thickness of the workpiece is obtained, and if the scanning area of the first-level laser scanner cannot cover the workpiece, the step is shifted to the fifth step;
and fifthly, calling a second-level laser scanner to acquire workpiece image information of a workpiece area which cannot be covered by the scanning area of the first-level laser scanner, splicing multi-frame scanning data from different levels of laser scanners into new image data, and generating a complete global 3D contour image so as to obtain the thickness of the workpiece.
Furthermore, the first-level laser scanner and the second-level laser scanner are fixed on the C-shaped steel structure, and when the conveying belt vibrates, the relative position between the upper laser scanner and the lower laser scanner of each group can be kept fixed, so that the precision and the stability of the measuring system are ensured; the C-shaped steel structure is connected with the Y-axis direction electric control track through the linear motor, the position of the laser scanner is adjusted according to the position and the size of the workpiece, and high flexibility is achieved; the terminal is connected with the CCD camera and the laser scanner and used for processing the acquired image data and controlling the motion state of the whole system.
Furthermore, two sets of laser scanners and CCD cameras are connected through a network adapter matched with the laser scanners, the calibrated coordinate system of the CCD cameras is used as a reference coordinate system, the two sets of laser scanners are calibrated through the calibration module of the terminal, and the laser scanners and the CCD cameras are unified under the same world coordinate system.
Furthermore, a set of laser emitter is respectively installed at two edges of a conveyor belt below the CCD camera, when a workpiece is placed into the conveyor belt and reaches a designated shooting area, a laser beam emitted by the laser emitter can be shielded, the laser emitter emits high and low level signals, and the level signals are transmitted into a terminal for data processing, so that the distance between the workpiece and the two sets of laser emitters is obtained, the placing position of the workpiece on the conveyor belt is obtained, and whether the workpiece reaches the designated shooting area of the CCD camera is judged.
Furthermore, the measuring system is used for measuring the thickness of a rigid workpiece or the thickness of a flexible workpiece, the distance between the joints of the conveyor belts at each stage is 15mm during installation, the conveyor belts support speed regulation, and the flexible workpiece can smoothly pass through the conveyor belts by means of self inertia by adjusting the running speed of the conveyor belts during measurement of workpieces with different flexibility degrees.
Further, the steps of calculating the minimum bounding rectangle of the workpiece and the vertex of the minimum bounding rectangle are as follows:
(1) one point P (x) in spacec,yc,zc) The coordinates of the corresponding projection points on the virtual imaging planes of the upper camera and the lower camera after perspective projection are respectively PL(UL,VL) And PR(UR,VR) From the similar triangle relationships, the following set of equations can be derived:
where f is the camera focal length and b is the distance between the camera projection centers;
in the formula (U)L,VL) And (U)R,VR) For the coordinates of the spatial coordinate point P in the upper and lower imaging coordinate systems, since the upper and lower images are coplanar, the difference value Disparity of the corresponding point is defined as the difference between the coordinates of the row of points in the upper image and the coordinates of the row of corresponding points in the lower image, and the mathematical expression is:
by combining the above two formulas, the three-dimensional coordinate of the scene midpoint P under the camera coordinate can be calculated as:
(2) calculating a three-dimensional coordinate image of the workpiece according to the obtained space three-dimensional point coordinates and the workpiece parallax image, and calculating a point cloud coordinate matrix according to the three-dimensional coordinate image:
(3) setting a point cloud barycentric coordinate as
In the formula, n represents the number of points, i represents a serial number, the coordinate system is translated to the point cloud gravity center position, and the point cloud coordinates under the new coordinate system are obtained as follows:
(4) calculating a yz plane under a new coordinate system to divide the point cloud into two parts, and then calculating new gravity center positions x of the two parts of the point cloudcore1、xcore2(ii) a After the xz plane divides the point cloud into two parts, the new gravity center position y of the two parts of the point cloudcore1、ycore2(ii) a The new barycentric position z of two-part point cloud after the point cloud is divided into two parts by xy planecore1、zcore2Calculating the distance d between each pair of centers of gravityx=||xcore2-xcore1||、dy=||ycore2-ycore1||、dz=||zcore2-zcore1||;
(5) Estimate the principal axis of inertia direction if dxAt maximum, the principal axis of inertia is in the direction vp=xcore1-xcore2If d isyAt maximum, the principal axis of inertia is in the direction vp=ycore1-ycore2If d iszAt maximum, the principal axis of inertia is in the direction vp=zcore1-zcore2;
(6) Taking the obtained principal axis of inertia as a new Z axis, calculating point cloud coordinates under the new principal axis, and calculating discrete points according to the point cloud coordinates under the new principal axisVertex coordinates of minimum bounding rectangle under new coordinate systemThe area of the rectangle is calculated by the vertex.
And further, judging whether the scanning area of the first-level laser scanner can cover the whole workpiece or not through the area of the minimum external rectangle, and calling the second-level laser scanner to splice the image data collected by the two groups of laser scanners if the scanning area can not cover the whole workpiece.
The invention discloses a multi-size workpiece thickness measuring system based on machine vision, which is characterized by comprising a data processing terminal, a workpiece detection unit, an image acquisition unit and a motion control unit;
the data processing terminal is used for storing and processing image data and controlling the operation of the whole system;
the workpiece detection unit is used for detecting whether the workpiece reaches a shooting area designated by the CCD camera;
the image acquisition unit is used for acquiring the position of a workpiece and shooting to acquire workpiece image information;
the motion control unit is used for adjusting the position of the laser scanner to reach a specified scanning area.
Has the advantages that: compared with the prior art, the invention has the following advantages:
(1) according to the invention, the measuring system can be automatically started through the sensor technology, and the positions of the cameras and the number of the adopted cameras are adjusted by judging the area of the workpiece to be measured, so that the whole process is highly automated, the manual intervention measuring links are reduced, and the labor cost is saved.
(2) The minimum circumscribed rectangle of the workpiece is obtained by calculating the inertia main shaft, and the method has the advantages of small calculation amount and high precision. The scanning range of the workpiece is judged by calculating the minimum external rectangle of the workpiece, the position of the laser scanner is adjusted through the vertex coordinate of the minimum external rectangle, the flexibility is high, the series number of the required laser scanner can be judged quickly and accurately when the shape and the size of the workpiece are more variable, and the position of the laser scanner can be adjusted in time.
(3) According to the invention, the three-dimensional laser scanner is selected to measure the thickness of the workpiece, so that the measurement difficulty is greatly reduced, and the measurement precision is improved.
(4) Structurally, this patent has adopted a C shaped steel structure to carry on three-dimensional laser scanner, also can guarantee during the conveyer belt vibration that the conveyer belt junction relative position of scanner keeps unanimous from top to bottom, has improved measurement system's stability and precision. The clearance between every grade conveyer belt sets up to 15mm and conveyer belt speed governing, can make different flexible degree work pieces can rely on self inertia to pass through the space between the two-stage conveyer belt smoothly through adjusting the functioning speed of conveyer belt.
Drawings
FIG. 1 is a flow chart of a measurement method of the present invention;
FIG. 2 is a schematic front view of a measurement platform;
FIG. 3 is a schematic top view of a metrology platform;
the figure shows that: 1-first order laser scanner; 2-a second level laser scanner; 3-a CCD camera; 4-Y axis direction electric control track; 5-a conveyor belt and 6-a workpiece to be detected; 7-C shaped steel structure; 8-a linear motor; 9-terminal.
Detailed Description
The invention is further described with reference to the following examples and the accompanying drawings.
The invention provides a machine vision-based multi-size workpiece thickness measuring system, which can measure the thickness of a workpiece with the area of 2L1*L2Within, thickness measurements (L) are made of workpieces having a thickness within W1For scanning the width of the area, L, by the laser scanner2For the conveyor length, W is the measurement range of the laser scanner). The measuring system consists of a data processing terminal, a workpiece detection unit, an image acquisition unit and a control unit. The image acquisition unit has two cascaded scanner groups, starts the first level only when the scanning area of the first level laser scanner group can cover the whole work piece, starts the second level when the scanning area of the first level laser scanner group can not cover the whole work piece. According to the parameters of the selected laser scanner, such as installation Clear Distance (CD), Measurement Range (MR), field of view (FOV) and the like, the scanning width of the single-stage laser scanner is determined to be L1The length of the single-stage conveyor belt is L2The area of the workpiece to be measured is limited to 2L1*L2Within. If the area of the workpiece exceeds the limited area, the number of groups of the laser scanners is increased, and if the increased number of groups is N, the limited area of the workpiece to be measured is (2+ N) L1*L2. The thickness range of the measured workpiece is determined according to the Measurement Range (MR) of the selected laser scanner, and if the measurement range is W, the thickness of the measured workpiece needs to be limited within W.
Specifically, in the embodiment of the present invention, the measuring system is a measuring platform, and as shown in fig. 2 and fig. 3, the main bodies of the measuring platform are a primary laser scanner 1, a secondary laser scanner 2, a CCD camera 3, a Y-axis direction electric control track 4, a conveyor belt 5, and a C-shaped steel structure 9. The CCD camera 3 is used to photograph the workpiece on the conveyor belt that enters the camera photographing area. Cascaded first level laser scanner 1, second level laser scanner 2 are fixed on C shape steel construction 7, when conveyer belt 5 has the vibration, can keep the relative position between two laser scanners about every level fixed, have guaranteed measurement system's precision and stability. The C-shaped steel structure 7 is connected with the Y-axis direction electric control track 4 through a linear motor 8 and can be used according to the working conditionsThe position and size of the member adjust the position of the laser scanner with a high degree of flexibility. The terminal 9 is connected with the CCD camera 3 and the laser scanner, and is used for processing the acquired image data and controlling the motion state of the entire system. The distance between the conveyor belts 5 of each stage is 15 mm. In order to improve the measurement accuracy as much as possible, the area of the workpiece 6 to be measured is limited to 2L according to the installation clearance, measurement range, field of view, and other parameters of the conventional laser scanner1*L2Within W, the thickness of the workpiece 6 to be measured is limited.
Secondly, connect through the network adapter with laser scanner adaptation between two sets of cascaded laser scanners and the CCD camera 3, regard the coordinate system of CCD camera 3 that has already markd as reference coordinate system again, calibrate two sets of laser scanners through the calibration module in the terminal, unify laser scanner and CCD camera 3 below same world coordinate system. The hardware of the terminal PC can be upgraded independently so as to meet the hardware configuration requirements of different requirements. The data transmission can adopt two modes of wire and wireless, the wire connection is more stable, but the wires are various and occupy large space; the wireless transmission connection is convenient, the occupied space is small, but the stability is poor, and the connection mode can be determined according to the actual use environment.
Fig. 1 is a flow chart of a measurement method of the present invention, which specifically includes the following steps:
s1: the system is started.
S2: and detecting whether the workpiece is placed in the conveyor belt and reaches a specified area.
The CCD camera comprises a CCD camera, wherein laser transmitters are installed at the edges of two sides of a conveyor belt below the CCD camera, when a workpiece is placed into the conveyor belt and arrives at a designated shooting area, laser beams sent by the laser transmitters can be shielded, so that the laser transmitters send high and low level signals, the level signals are transmitted into a terminal for data processing, the distance between the workpiece and two groups of laser transmitters is obtained, and therefore the placing position of the workpiece on the conveyor belt is obtained, and whether the workpiece arrives at the designated shooting area of the CCD camera 3 is judged.
S3: and if the detected workpiece is not placed in the conveyor belt and reaches the designated area, the system is in standby.
S4: the position of the workpiece is manually adjusted to enter the shooting area of the CCD camera 3.
S5: when the workpiece reaches the designated shooting area of the CCD camera 3, the CCD camera 3 takes an image of the workpiece and sends the image to the terminal 11.
S6: and calling an image processing module to perform image processing, and calculating the minimum external rectangle of the workpiece.
The method comprises the following specific steps:
(1) the pixels in the color image are divided into three components of R, G and B, the three components range from [0,255], and the acquired color image is converted into a gray image by adopting the following weighted average formula:
A=0.3*R+0.59*G+0.11*B
(2) and performing linear filtering on the image by adopting a domain averaging algorithm, and moving the filter point by point on the image so as to smooth the whole image.
(3) After the gray scale image conversion and the image filtering are performed, the edge detection needs to be performed on the workpiece to be detected. And (4) extracting a linear edge capable of representing the workpiece to be detected by adopting Hough transformation on the image.
(4) One point P (x) in spacec,yc,zc) The coordinates of the corresponding projection points on the virtual imaging planes of the upper camera and the lower camera after perspective projection are respectively PL(UL,VL) And PR(UR,VR). From the similar triangular relationships, the following set of equations can be derived:
where f is the camera focal length and b is the distance between the camera projection centers.
In the formula (U)L,VL) And (U)R,VR) For the coordinates of the spatial coordinate point P in the upper and lower imaging coordinate systems, since the upper and lower images are coplanar, the difference value of the corresponding point is defined as the difference between the coordinates of the row of points in the upper image and the coordinates of the row of corresponding points in the lower image, and the mathematical expression is:
by combining the above two formulas, the three-dimensional coordinate of the scene midpoint P under the camera coordinate can be calculated as:
(5) calculating a three-dimensional coordinate image of the workpiece according to the obtained space three-dimensional point coordinates and the workpiece parallax image, and calculating a point cloud coordinate matrix according to the three-dimensional coordinate image:
(6) setting a point cloud barycentric coordinate as
In the formula, n represents the number of points, i represents a serial number, and the coordinate system is translated to the point cloud gravity center position to obtain the point cloud coordinate under a new coordinate system:
(7) calculating a yz plane under a new coordinate system to divide the point cloud into two parts, and then calculating new gravity center positions x of the two parts of the point cloudcore1、xcore2(ii) a After the xz plane divides the point cloud into two parts, the new gravity center position y of the two parts of the point cloudcore1、ycore2(ii) a The new barycentric position z of two-part point cloud after the point cloud is divided into two parts by xy planecore1、zcore2Calculating the distance d between each pair of centers of gravityx=||xcore2-xcore1||、dy=||ycore2-ycore1||、dz=||zcore2-zcore1||;
(8) The principal axis of inertia direction is estimated. If d isxAt maximum, the principal axis of inertia is in the direction vp=xcore1-xcore2If d isyAt maximum, the principal axis of inertia is in the direction vp=ycore1-ycore2If d iszAt maximum, the principal axis of inertia is in the direction vp=zcore1-zcore2。
(9) And taking the obtained inertia main shaft as a new Z axis, and calculating the point cloud coordinate under the new main shaft. Calculating discrete points by point cloud coordinates under new main shaftVertex coordinates of the minimum bounding rectangleThe area of the rectangle can be calculated from the vertices.
S7: and judging whether the scanning area of the single group of laser scanners can cover the whole workpiece or not through the minimum circumscribed rectangular area.
Specifically, because the accuracy needs to be improved as much as possible during measurement, the distance between the laser scanner and the conveyor belt is short when the laser scanner is installed, the field of view of the laser scanner is relatively narrow, and whether the single-group laser scanner can complete scanning of the workpiece at one time needs to be judged according to the area of the minimum external rectangle of the workpiece.
S8: if the first level laser scanner 1 cannot complete the scanning of the workpiece at one time, the second level laser scanner 2 is called.
S9: and adjusting the position of the laser scanner according to the coordinates of each vertex of the minimum circumscribed rectangle.
Specifically, be connected through the network adapter with laser scanner adaptation between two sets of laser scanner and the CCD camera, regard the coordinate system of the CCD camera that has markd as reference coordinate system again, calibrate two sets of laser scanner through the calibration module in the terminal, unify laser scanner and CCD camera under same world coordinate system. According to the calculated vertex coordinates of the minimum external rectangle, the terminal controls the linear motor located on the Y-axis direction electric control track to move, and the linear motor carries the laser scanner to reach the position where the surface information of the workpiece can be completely collected.
S10: the laser scanner scans the workpiece to acquire image information of the surface of the workpiece.
S11: and splicing the image data acquired by the two groups of laser scanners by using an image splicing technology.
Specifically, image stitching adopts a region correlation-based stitching algorithm, and the method starts from the gray value of an image to be stitched, calculates the difference of the gray value of a region in the image to be registered and a region with the same size in a reference image by using a least square method or other mathematical methods, compares the difference and then judges the similarity degree of the overlapping region of the image to be stitched, thereby obtaining the range and the position of the overlapping region of the image to be stitched, realizing the image stitching and obtaining a complete workpiece image.
S12: the terminal 9 generates a complete 3D global scanning contour map according to the acquired image data, so as to obtain the thickness of the workpiece.
The above examples are only preferred embodiments of the present invention, it should be noted that: it will be apparent to those skilled in the art that various modifications and equivalents can be made without departing from the spirit of the invention, and it is intended that all such modifications and equivalents fall within the scope of the invention as defined in the claims.
Claims (7)
1. A method for measuring the thickness of a multi-size workpiece based on machine vision is characterized by comprising the following steps:
step one, starting a system, executing step two if a workpiece is detected to enter a shooting area of a CCD camera, otherwise, waiting for the system, and judging again after adjusting the placing position of the workpiece;
secondly, when the workpiece enters a shooting area of the CCD camera, the camera shoots a two-dimensional image of the workpiece;
thirdly, the terminal calls a processing module to perform image processing on the shot workpiece image, the edge contour of the workpiece is detected, the minimum circumscribed rectangle of the workpiece is generated according to the detected contour, and coordinates of four vertexes of the circumscribed rectangle are obtained;
the terminal adjusts the position of the laser scanner according to the coordinates of the vertex of the minimum circumscribed rectangle, judges whether the laser scanning area of the first-level laser scanner can cover the whole workpiece or not according to the area of the minimum circumscribed rectangle, if the laser scanning area can cover the whole workpiece, the three-dimensional image of the workpiece can be generated according to the scanned surface image of the workpiece, so that the thickness of the workpiece is obtained, and if the scanning area of the first-level laser scanner cannot cover the workpiece, the step is shifted to the fifth step;
and fifthly, calling a second-level laser scanner to acquire workpiece image information of a workpiece area which cannot be covered by the scanning area of the first-level laser scanner, splicing multi-frame scanning data from different levels of laser scanners into new image data, and generating a complete global 3D contour image so as to obtain the thickness of the workpiece.
2. The method for measuring the thickness of the multi-size workpiece based on the machine vision is characterized in that the first-stage laser scanner and the second-stage laser scanner are fixed on a C-shaped steel structure, so that when the workpiece is conveyed with vibration, the relative position between the upper laser scanner and the lower laser scanner of each group can be kept fixed, and the precision and the stability of a measuring system are ensured; the C-shaped steel structure is connected with the Y-axis direction electric control track through the linear motor, the position of the laser scanner is adjusted according to the position and the size of the workpiece, and high flexibility is achieved; the terminal is connected with the CCD camera and the laser scanner and used for processing the acquired image data and controlling the motion state of the whole system.
3. The method of claim 2, wherein the method comprises the following steps: the two sets of laser scanners and the CCD cameras are connected through network adapters matched with the laser scanners, the coordinate system of the calibrated CCD cameras is used as a reference coordinate system, the two sets of laser scanners are calibrated through the calibration module of the terminal, and the laser scanners and the CCD cameras are unified under the same world coordinate system.
4. The method for measuring the thickness of the multi-size workpiece based on the machine vision as claimed in claim 1, wherein a group of laser emitters are respectively installed at two edges of a conveyor belt below the CCD camera, when the workpiece is placed on the conveyor belt and reaches a designated shooting area, a laser beam emitted by the laser emitters is shielded, the laser emitters emit high and low level signals, the level signals are transmitted to a terminal for data processing, the distance between the workpiece and the two groups of laser emitters is obtained, and therefore the placement position of the workpiece on the conveyor belt is obtained and whether the workpiece reaches the designated shooting area of the CCD camera is judged.
5. The method for measuring the thickness of the multi-size workpiece based on the machine vision is characterized in that the system is used for measuring the thickness of a rigid workpiece or measuring the thickness of a flexible workpiece, the distance between the joints of the conveyor belts at each stage is 15mm when the system is installed, the speed regulation is supported by the conveyor belts, and the flexible workpiece can smoothly pass through the conveyor belts by means of self inertia when the workpieces with different flexibility degrees are measured by adjusting the running speed of the conveyor belts.
6. The method of claim 1, wherein the step of calculating the minimum bounding rectangle of the workpiece and the vertex of the minimum bounding rectangle is as follows:
(1) one point P (x) in spacec,yc,zc) The coordinates of the corresponding projection points on the virtual imaging planes of the upper camera and the lower camera after perspective projection are respectively PL(UL,VL) And PR(UR,VR) From the similar triangle relationships, the following set of equations can be derived:
where f is the camera focal length and b is the distance between the camera projection centers;
in the formula (U)L,VL) And (U)R,VR) For the coordinates of the spatial coordinate point P in the upper and lower imaging coordinate systems, since the upper and lower images are coplanar, the difference value Disparity of the corresponding point is defined as the difference between the coordinates of the row of points in the upper image and the coordinates of the row of corresponding points in the lower image, and the mathematical expression is:
by combining the above two formulas, the three-dimensional coordinate of the scene midpoint P under the camera coordinate can be calculated as:
(2) calculating a three-dimensional coordinate image of the workpiece according to the obtained space three-dimensional point coordinates and the workpiece parallax image, and calculating a point cloud coordinate matrix according to the three-dimensional coordinate image:
(3) setting a point cloud barycentric coordinate as
In the formula, n represents the number of points, i represents a serial number, the coordinate system is translated to the point cloud gravity center position, and the point cloud coordinates under the new coordinate system are obtained as follows:
(4) calculating a yz plane under a new coordinate system to divide the point cloud into two parts, and then calculating new gravity center positions x of the two parts of the point cloudcore1、xcore2(ii) a After the xz plane divides the point cloud into two parts, the new gravity center position y of the two parts of the point cloudcore1、ycore2(ii) a The new barycentric position z of two-part point cloud after the point cloud is divided into two parts by xy planecore1、zcore2Calculating the distance d between each pair of centers of gravityx=||xcore2-xcore1||、dy=||ycore2-ycore1||、dz=||zcore2-zcore1||;
(5) Estimate the principal axis of inertia direction if dxAt maximum, the principal axis of inertia is in the direction vp=xcore1-xcore2If d isyAt maximum, the principal axis of inertia is in the direction vp=ycore1-ycore2If d iszAt maximum, the principal axis of inertia is in the direction vp=zcore1-zcore2;
(6) Taking the obtained principal axis of inertia as a new Z axis, calculating point cloud coordinates under the new principal axis, and calculating discrete points according to the point cloud coordinates under the new principal axisVertex coordinates of minimum bounding rectangle under new coordinate systemThe area of the rectangle is calculated by the vertex.
7. The method of claim 1 for measuring the thickness of a multi-dimensional workpiece based on machine vision, wherein the method comprises the following steps: whether the scanning area of the first-level laser scanner can cover the whole workpiece is judged through the area of the minimum external rectangle, if the whole workpiece cannot be covered, the second-level laser scanner is called, and image data collected by the two groups of laser scanners are spliced.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010481273.8A CN111609801B (en) | 2020-05-31 | 2020-05-31 | Multi-size workpiece thickness measuring method and system based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010481273.8A CN111609801B (en) | 2020-05-31 | 2020-05-31 | Multi-size workpiece thickness measuring method and system based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111609801A CN111609801A (en) | 2020-09-01 |
CN111609801B true CN111609801B (en) | 2021-03-23 |
Family
ID=72198101
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010481273.8A Active CN111609801B (en) | 2020-05-31 | 2020-05-31 | Multi-size workpiece thickness measuring method and system based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111609801B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112595252A (en) * | 2020-12-22 | 2021-04-02 | 航天智造(上海)科技有限责任公司 | Handheld clearance and surface difference vision measuring equipment |
CN113155198A (en) * | 2021-05-08 | 2021-07-23 | 上海海洋大学 | Automatic measuring equipment and method for weight and overall dimension of fish body |
CN113587829B (en) * | 2021-09-03 | 2023-08-01 | 凌云光技术股份有限公司 | Edge thickness measuring method and device, edge thickness measuring equipment and medium |
CN113849000B (en) * | 2021-09-15 | 2024-03-29 | 山东泰开智能配电有限公司 | Control method of automatic detection system for plating thickness of silver plating piece of high-voltage isolating switch |
CN114199142A (en) * | 2021-12-08 | 2022-03-18 | 国际竹藤中心 | Measuring device |
CN114200532B (en) * | 2021-12-14 | 2024-05-14 | 中国航发南方工业有限公司 | Device and method for detecting residues in casting case of aero-engine |
CN114324363B (en) * | 2021-12-31 | 2024-04-26 | 无锡艾方芯动自动化设备有限公司 | Product state detection method and system |
CN115791830A (en) * | 2022-12-07 | 2023-03-14 | 中国联合网络通信集团有限公司 | Steel plate detection system, steel plate detection method and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108895958A (en) * | 2018-03-31 | 2018-11-27 | 广州市华冠精冲零件有限公司 | A kind of automobile speed-changing box pulling fork part method for comprehensive detection and system |
CN108955547A (en) * | 2018-06-29 | 2018-12-07 | 苏州富强科技有限公司 | A kind of Workpiece structure size detecting device |
CN109540027A (en) * | 2018-10-11 | 2019-03-29 | 伍波 | A kind of quick 3D vision laser measurement localization method |
CN109631766A (en) * | 2018-12-11 | 2019-04-16 | 南京第五十五所技术开发有限公司 | A kind of wood plank dimension measurement method based on image |
EP3184958B1 (en) * | 2015-12-23 | 2020-03-18 | Liebherr-Verzahntechnik GmbH | Apparatus for emptying a conveyor with an apparatus for workpiece identification and/or workpiece position detection of a plurality of arbitrary disposed workpieces within the conveyor and gripping apparatus for emptying the conveyor |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SG10201803290VA (en) * | 2018-04-19 | 2019-11-28 | Emage Vision Pte Ltd | System and method for inspecting optical power and thickness of ophthalmic lenses immersed in a solution |
-
2020
- 2020-05-31 CN CN202010481273.8A patent/CN111609801B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3184958B1 (en) * | 2015-12-23 | 2020-03-18 | Liebherr-Verzahntechnik GmbH | Apparatus for emptying a conveyor with an apparatus for workpiece identification and/or workpiece position detection of a plurality of arbitrary disposed workpieces within the conveyor and gripping apparatus for emptying the conveyor |
CN108895958A (en) * | 2018-03-31 | 2018-11-27 | 广州市华冠精冲零件有限公司 | A kind of automobile speed-changing box pulling fork part method for comprehensive detection and system |
CN108955547A (en) * | 2018-06-29 | 2018-12-07 | 苏州富强科技有限公司 | A kind of Workpiece structure size detecting device |
CN109540027A (en) * | 2018-10-11 | 2019-03-29 | 伍波 | A kind of quick 3D vision laser measurement localization method |
CN109631766A (en) * | 2018-12-11 | 2019-04-16 | 南京第五十五所技术开发有限公司 | A kind of wood plank dimension measurement method based on image |
Also Published As
Publication number | Publication date |
---|---|
CN111609801A (en) | 2020-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111609801B (en) | Multi-size workpiece thickness measuring method and system based on machine vision | |
CN107578464B (en) | Conveyor belt workpiece three-dimensional contour measuring method based on line laser scanning | |
US9672630B2 (en) | Contour line measurement apparatus and robot system | |
US9025857B2 (en) | Three-dimensional measurement apparatus, measurement method therefor, and computer-readable storage medium | |
US11243072B2 (en) | Method for the three dimensional measurement of moving objects during a known movement | |
US8032327B2 (en) | Auto-referenced sensing method for three-dimensional scanning | |
US9488469B1 (en) | System and method for high-accuracy measurement of object surface displacement using a laser displacement sensor | |
CN112161619B (en) | Pose detection method, three-dimensional scanning path planning method and detection system | |
CN113674345B (en) | Two-dimensional pixel-level three-dimensional positioning system and positioning method | |
US20200124406A1 (en) | Method for referencing a plurality of sensors and associated measuring device | |
CN116958146B (en) | Acquisition method and device of 3D point cloud and electronic device | |
KR20240040708A (en) | Board measurement system and method thereof | |
CN112767338A (en) | Assembled bridge prefabricated part hoisting and positioning system and method based on binocular vision | |
US12058468B2 (en) | Image capturing apparatus, image processing apparatus, image processing method, image capturing apparatus calibration method, robot apparatus, method for manufacturing article using robot apparatus, and recording medium | |
CN114396875A (en) | Rectangular parcel volume measurement method based on vertical shooting of depth camera | |
CN114964007A (en) | Visual measurement and surface defect detection method for weld size | |
CN110044266B (en) | Photogrammetry system based on speckle projection | |
CN106942813B (en) | non-contact measurement method for conveniently acquiring human body data | |
Bergström et al. | Automatic in-line inspection of shape based on photogrammetry | |
US20230016639A1 (en) | System and method for controlling automatic inspection of articles | |
CN113963054A (en) | Intelligent express box size measuring method and system based on binocular camera | |
CN209342062U (en) | 3D vision guide de-stacking measuring system | |
JP2004028811A (en) | Device and method for correcting distance for monitoring system | |
JP3221384B2 (en) | 3D coordinate measuring device | |
Botterill et al. | Design and calibration of a hybrid computer vision and structured light 3D imaging system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |