CN113222986A - Continuous casting billet angular point and edge contour point set positioning method, system, medium and device - Google Patents
Continuous casting billet angular point and edge contour point set positioning method, system, medium and device Download PDFInfo
- Publication number
- CN113222986A CN113222986A CN202110625271.6A CN202110625271A CN113222986A CN 113222986 A CN113222986 A CN 113222986A CN 202110625271 A CN202110625271 A CN 202110625271A CN 113222986 A CN113222986 A CN 113222986A
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- point set
- line
- edge
- image
- 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
- 238000009749 continuous casting Methods 0.000 title claims abstract description 189
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000013519 translation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30116—Casting
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method, a system, a medium and a device for positioning continuous casting corner points and edge contour point sets, wherein the method comprises the following steps: shooting a continuous casting billet image and preprocessing the continuous casting billet image to obtain a multi-line structured light point set image; processing the images of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set; acquiring a continuous casting billet horizontal direction edge point set and a continuous casting billet vertical direction edge point set by extraction based on the line structure light edge point set, and acquiring a continuous casting billet angular point based on the continuous casting billet horizontal direction edge point set and the continuous casting billet vertical direction edge point set; and extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting billet edge point coordinates based on the line structure light center line point set. The invention discloses a method, a system, a medium and a device for positioning a continuous casting corner point and edge contour point set, which are used for realizing the non-contact automatic positioning of the continuous casting corner point and the edge contour point.
Description
Technical Field
The invention relates to the technical field of positioning, in particular to a continuous casting corner and edge contour point set positioning method, a system, a medium and a device.
Background
The positioning of the continuous casting corner points and the edge contour point sets is an essential link in the aspects of continuous casting production, processing, quality detection and the like, and the positioning precision directly influences the production precision of the continuous casting, the quality and other indexes, so that the positioning method is very important. In the continuous casting billet production process, edge defects and other problems are easy to occur, so that the quality of the continuous casting billet is ensured by frequently carrying out edge cutting treatment. But the production field environment of the continuous casting billet is severe, the difficulty of contact type positioning of the edge of the continuous casting billet is high, and the efficiency is low.
Therefore, it is desirable to solve the problem of positioning the corner points and edge contour point sets of the continuous casting slab without contact.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a method, a system, a medium, and a device for positioning a corner point and an edge contour point set of a continuous casting slab, which are used to solve the problem of how to position the corner point and the edge contour point set of the continuous casting slab without contact in the prior art.
In order to achieve the above and other related objects, the present invention provides a method for positioning corner points and edge contour point sets of a continuous casting slab, comprising the following steps: shooting a continuous casting billet image and preprocessing the continuous casting billet image to obtain a multi-line structured light point set image; processing the images of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set; acquiring a continuous casting billet horizontal direction edge point set and a continuous casting billet vertical direction edge point set by extracting a central line end point of the line structure light edge point set based on the line structure light edge point set, and acquiring a continuous casting billet angular point based on the continuous casting billet horizontal direction edge point set and the continuous casting billet vertical direction edge point set; and extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting billet edge point coordinates based on the line structure light center line point set.
In order to achieve the above object, the present invention further provides a system for positioning corner points and edge contour point sets of a continuous casting slab, comprising: the device comprises a shooting module, a preprocessing module, a first extraction module and a second extraction module; the shooting module is used for shooting images of continuous casting billets and carrying out pretreatment to obtain images of a multi-line structured light point set; the preprocessing module is used for processing the images of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set; the first extraction module is used for extracting the central line end point of the line structure light edge point set to obtain a continuous casting blank horizontal direction edge point set and a continuous casting blank vertical direction edge point set, and obtaining a continuous casting blank angular point based on the continuous casting blank horizontal direction edge point set and the continuous casting blank vertical direction edge point set; the second extraction module is used for extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting blank edge point coordinates based on the line structure light center line point set.
In order to achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements any of the above methods for positioning corner points and edge contour point sets of a continuous casting slab.
In order to achieve the above object, the present invention further provides a continuous casting corner and edge contour point set positioning device, including: a processor and a memory; the memory is used for storing a computer program; the processor is connected with the memory and is used for executing the computer program stored in the memory so as to enable the continuous casting corner point and edge contour point set positioning device to execute any continuous casting corner point and edge contour point set positioning method.
As described above, the method, system, medium and apparatus for locating the corner points and edge contour point sets of a continuous casting slab of the present invention have the following advantages: the method is used for realizing the non-contact automatic positioning of the angular points and the edge contour points of the continuous casting billets.
Drawings
FIG. 1a is a schematic view of an application scenario architecture of the method for locating corner points and edge contour point sets of a continuous casting slab according to an embodiment of the present invention;
FIG. 1b is a flowchart illustrating an embodiment of a method for positioning corner points and edge contour point sets of a continuous casting slab according to the present invention;
FIG. 1c is a schematic view of sub-pixel positions of a corner point and an edge contour point set of a continuous casting slab according to an embodiment of the present invention;
FIG. 1d is a diagram showing the effect of the horizontal and vertical center line extraction process of the continuous casting corner and edge contour point set positioning method in one embodiment of the present invention;
FIG. 1e is a detailed diagram showing the effect of the horizontal and vertical center line extraction process of the continuous casting corner and edge contour point set positioning method in one embodiment of the present invention;
FIG. 1f is a diagram showing the positioning effect of the corner point of the continuous casting slab in an embodiment of the positioning method for the corner point and edge contour point set of the continuous casting slab of the present invention;
FIG. 1g is a diagram illustrating the positioning effect of the edge contour points in an embodiment of the corner points and edge contour point set positioning method of the invention;
fig. 1h is a schematic diagram of a situation in which the corner point and edge contour point set positioning method of the invention needs to realize the corner point positioning of the continuous casting slab through splicing in one example.
FIG. 2 is a schematic structural diagram of a system for locating corner points and edge contour point sets of a continuous casting slab according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an embodiment of the corner point and edge contour point set positioning device of the invention.
Description of the element reference numerals
21 shooting module
22 preprocessing module
23 first extraction module
24 second extraction module
31 processor
32 memory
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, so that the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, the type, quantity and proportion of the components in actual implementation can be changed freely, and the layout of the components can be more complicated.
The invention discloses a method, a system, a medium and a device for positioning a continuous casting corner point and edge contour point set, which are used for realizing the non-contact automatic positioning of the continuous casting corner point and the edge contour point.
As shown in fig. 1a, the method, system, medium and apparatus for locating continuous casting corner points and edge contour point sets of the present invention are applied to the application scenarios of a laser 11, a camera 12 and a continuous casting 13. The laser machine sends line structure light 14 to on the continuous casting billet, the camera is used for shooing the photo of continuous casting billet, handles, finally realizes continuous casting billet angular point and edge contour point contactless automatic positioning.
As shown in fig. 1b, in an embodiment, the method for positioning corner points and edge contour point sets of a continuous casting slab of the present invention comprises the following steps:
and step S11, shooting images of the continuous casting billet and preprocessing the images to obtain a multi-line structured light point set image.
Specifically, the shooting of the continuous casting billet image and the preprocessing of the continuous casting billet image to obtain the light spot set image with the multi-line structure comprises the following steps: projecting multi-line structured light onto a continuous casting billet based on a laser to shoot a first continuous casting billet image containing the multi-line structured light, and directly shooting a second continuous casting billet image without projecting the multi-line structured light; and performing difference processing on the first continuous casting blank image and the second continuous casting blank image to obtain a multi-line structured light point set image.
And step S12, processing the multi-line structured light point set image based on a preset algorithm to obtain a line structured light edge point set.
Specifically, the obtaining of the line-structured light edge point set by processing the image of the multi-line-structured light point set based on a preset algorithm includes:
and S121, performing line structure light edge extraction on the line structure light point set image based on a preset sub-pixel algorithm to obtain an edge discrete point set. The preset sub-pixel algorithm comprises the following steps: canny based Devernay subpixel algorithm. Specifically, the Devernay subpixel algorithm based on Canny is used for performing subpixel-level edge extraction on the line structured light, so that accurate positioning of a line structured light center point set is completed. And the method also comprises the step of carrying out noise reduction treatment on the edge discrete point set, specifically, carrying out convolution on the edge discrete point set after the edge discrete point set is converted into a gray level image and a Gaussian kernel function, realizing Gaussian smooth filtering, reducing the influence caused by noise as much as possible, and reducing the error rate.
The procedure is represented as follows:
I*KS→Is
wherein I is a gray scale image to be processed, KSIs a Gaussian kernel function, ISIs the image obtained after filtering.
And S122, screening connecting lines according to the pixel distance and the dividing range in the horizontal and vertical directions to obtain a line set.
Specifically, the gradient value of an image often contains abundant image information, and generally speaking, when an edge exists in the image, a larger gradient value is required. Therefore, the Canny-based Devernay edge detection algorithm mainly finds the image I from the horizontal direction and the vertical direction respectivelyS(x, y) gradient values, the process is represented as follows:
IS(x+1,y)-IS(x-1,y)→gx(x,y)
IS(x,y+1)-IS(x,y-1)→gy(x,y)
wherein, gx(x, y) is the gradient in the horizontal direction at point (x, y)Value gy(x, y) is a gradient value in the vertical direction at the point (x, y).
(gx,gy)→g
g is an image ISGradient vector field at point (x, y). Knowing gx(x, y) is the gradient value in the horizontal direction at point (x, y), and gy(x, y) is a gradient value in the vertical direction at the point (x, y). G is obtained as image ISGradient vector field at point (x, y).
In order to improve the positioning precision, the invention extracts the edge point set of the sub-pixel level. Devernay defines the point with the largest interpolation of adjacent gradient module values as an edge point, so that the edge point can be determined by calculating the quadratic interpolation of the gradient module values at the adjacent points in the gradient direction, and here, the calculation process is described by taking the adjacent three points as an example, and the details are as follows:
suppose A, B, C are images ISThe gradient module values of three adjacent pixel points on (x, y) are expressed as | | | g (a) |, | g (b) |, | g (c) |, respectively, as shown in fig. 1c, a sub-pixel position η may exist, and the gradient module values are greater than | | | g (a) |, | g (b) |, | g (c) |, obviously, the sub-pixel position η more conforms to the edge. On the premise that the calculation cost is as small as possible, Devernay gives a method for calculating the sub-pixel position eta:
relative to vector
The offset of the sub-pixel position η is:
to reduce the error, the following correction is made:
when the gradient at the point (x, y) satisfies the following three conditions, the point is determined as a horizontal direction edge point:
when the gradient at the point (x, y) satisfies the following three conditions, the point is determined as a vertical direction edge point:
when | gx(x,y)|＝|gy(x, y) |, the default is the horizontal direction edge point.
The independent edge pixel point sets are obtained through the steps, and the pixel point sets belonging to the same edge contour are required to be grouped together to form the contour. Taking the pixel points a and B as an example, the pixel points classified as the same link should satisfy the following two conditions:
the included angle of the gradient direction is less than 90 degrees, and the mathematical expression is as follows: g (A) g (B) > 0;
the continuous link can divide the dark area to the same side of the curve and can pass through the vector
Whether one of the two gradient directions possible with point a is orthogonal or not.
Thus, the horizontal direction edge point or the vertical direction edge point is obtained according to the pixel distance and the division range of the horizontal and vertical directions. After the edge points in the horizontal direction or the edge points in the vertical direction are obtained, whether the independent edge pixel point sets obtained in the above steps are pixel points of the same link is judged according to the above two conditions, and the pixel points of the same link are connected to obtain a line set.
And screening the obtained line set according to the length and the interval of the line segment to obtain the screened line set.
And S123, sequencing the screened line set according to the coordinate values to obtain a line structured light edge point set.
Specifically, the line sets are sequentially sorted according to the magnitude of the coordinate values to obtain the line-structured light edge point set.
Specifically, the method further comprises the step of carrying out noise reduction processing on the structured light edge point set. To account for some edge pixels due to noise and color variations, a dual threshold is used in the present inventionValue method. Setting the high threshold value as T2The low threshold is T1. If the edge pixel gradient value of the line structure light edge point set is higher than T2Then it is marked as a strong edge pixel; if the gradient value of the edge pixel is between T1And T2If so, marking the pixel as a weak edge pixel; if the edge pixel gradient value is below T1It is suppressed.
The strong edge point can be regarded as a real edge point, and the weak edge point is possibly caused by the change of factors such as noise, so that the 8-connected neighborhood pixels of the weak edge point are detected, and if the strong edge point exists, the weak edge point is regarded as a real edge point and reserved.
Step S13, when at least two line structure lights are shot in the continuous casting billet image, which projects the line structure lights, in the horizontal direction and the vertical direction (namely, when the line structure lights in the image are enough in quantity), the edge point set in the horizontal direction of the continuous casting billet and the edge point set in the vertical direction of the continuous casting billet can be obtained by extracting the central line end point of the line structure light based on the line structure light edge point set, and the continuous casting billet corner point is obtained based on the continuous casting billet edge point set in the horizontal direction and the continuous casting billet edge point set in the vertical direction. Specifically, the obtaining of the continuous casting corner point based on the linear structured light edge point set by extracting a continuous casting horizontal direction edge point set and a continuous casting vertical direction edge point set includes:
s131, acquiring a vertical coordinate intermediate value based on the linear structure light edge point set to obtain a central line of the linear structure light in the horizontal direction, and acquiring an end point of the central line of the linear structure light in the horizontal direction to become a continuous casting blank vertical direction edge point set.
Specifically, for the left and right edges of the line structure light edge point set, the horizontal coordinate median is taken to obtain the central line of the line structure light in the vertical direction, and the end point of the central line of the line structure light in the horizontal direction is obtained to be the continuous casting billet vertical direction edge point set.
Step S132, acquiring a horizontal coordinate intermediate value based on the line structure light edge point set to obtain a vertical line structureThe central line of the light, the central line end point of the line structure light in the vertical direction is obtained to be a continuous casting billet horizontal direction edge point set, and the coordinate is expressed as { (x)h1，yh1)，(xh2，yh2),…,(xhn，yhn) (where n denotes the number of lines of the vertical line structure). For the upper edge and the lower edge of the line structure light edge point set, taking a vertical direction coordinate median value to obtain a central line of the line structure light in the horizontal direction, obtaining a central line endpoint of the line structure light in the horizontal direction to become a continuous casting billet vertical direction edge point set, and expressing coordinates as { (x)v1，yv1),(xv2，yv2),…,(xvm，yvm) (where m denotes the number of horizontal line structured light bars). And S133, connecting two end points of the edge point set in the vertical direction of the continuous casting billet into a first straight line.
Taking two edge points (x) of edge point set in vertical direction of continuous casting billetv1，yv1),(xv2，yv2) Making a first straight line:
yv＝k1xv+b1and S134, connecting two end points of the edge point set of the continuous casting slab in the horizontal direction into a second straight line.
Taking two edge points (x) of edge point set in horizontal direction of continuous casting billeth1，yh1),(xh2，yh2) And making a second straight line:
yh＝k2xh+b2
and S135, the intersection point of the first straight line and the second straight line is the angular point of the continuous casting slab.
Finding a straight line yvAnd yhThe intersection point of the two points is the angular point of the continuous casting billet.
Or in another embodiment, in step S13, when there are not at least two line-structured lights in the horizontal and vertical directions in the shot continuous casting image projected with the line-structured light (i.e., when the number of the line-structured lights in the image is not enough), the horizontal edge point set and the vertical edge point set of the continuous casting may be obtained by extracting the central line point of the line-structured light edge point set, and the angular point of the continuous casting may be obtained based on the horizontal edge point set and the vertical edge point set of the continuous casting. Specifically, the obtaining of the continuous casting corner point based on the linear structured light edge point set by extracting a continuous casting horizontal direction edge point set and a continuous casting vertical direction edge point set includes:
when the number of the line-structured light in the vertical direction in the shot continuous casting billet image projected with the line-structured light is less than two (as shown in an area 1 of fig. 1 h), the point set in the step S13 cannot be directly obtained from the image, so that a splicing module needs to be added to perform coordinate conversion on the line-structured light point set on the subsequent continuous casting billet image (as shown in an area 2 of fig. 1 h), so that at least two line-structured light in the vertical direction are on the continuous casting billet, thereby obtaining the target structured light point set in the step S13, and then the continuous casting billet corner point can be obtained by operating according to the step S13.
Specifically, taking the vertical direction as an example, as shown in fig. 1h, only one line structure light in the vertical direction in the region 1 image is available, and a sufficient line structure light center point cannot be extracted to be used as the second straight line in step S134, so that the region 2 image needs to be used to convert the point set coordinates of the line structure light 18 into the region 1 image coordinate system through stitching. And S132, acquiring a horizontal coordinate intermediate value based on the linear structure light edge point set to obtain a central line of the linear structure light in the vertical direction, and acquiring a central line endpoint of the linear structure light in the vertical direction to become a continuous casting blank horizontal direction edge point set.
And then, executing step S133, when the angular points of the continuous casting billet cannot be positioned due to insufficient quantity of line structure light on the image, performing coordinate conversion by using a homography matrix, so that at least two line structure light in the horizontal direction and the vertical direction in the image are on the continuous casting billet.
Step S1331 of utilizing Zhangyingyou scaling methodObtaining the internal reference matrices K of the camera 15 and the camera 16, respectively1、K2And a rotation matrix R of the camera 15 and the slab plane 191And translation vector T1Rotation matrix R of camera 16 and strand plane 192And translation vector T2。
Step S1332, obtaining three-dimensional coordinates { (x) of a group of points on the continuous casting slab plane 19 in the coordinate system of the camera 15 by means of the calibration result in the step S141 in combination with the linear structured light plane calibration1，y1，z1),(x2，y2，z2) … and each point corresponds to a three-dimensional coordinate { (x) within the camera 16 coordinate system1′，y1′，z1′),(x′2,y2′,z2'), … }, the rotation matrix R and the translation vector T between the cameras 15 and 16 are found.
Step S1333, acquiring a homography matrix H between the region 1 image and the region 2 image.
Specifically, a world coordinate system is established at a position coinciding with a camera 16 coordinate system, a distance from a continuous casting slab plane 19 to an origin O of the camera 16 coordinate system is set as d, and a specific calculation method is as follows:
finding a point M on the plane 19 of the continuous casting billet, and setting the world coordinates as (X, Y, Z), the pixel coordinates on the imaging plane of the camera 16 as (u, v), and the coordinates of the central point of the image as (u, v)0，v0) Then, according to the camera imaging model, combining the triangle similarity principle, we can obtain:
Z＝d
wherein f isx，fyThe focal lengths of the camera in the x and y directions, respectively. The world coordinates (X, Y, Z) of M may be obtained based on the calibration result in step S141 in combination with the line structured light plane calibration, and the coordinate value in the Z direction is d.
Let the unit normal vector of the slab plane 19 in the coordinate system of the camera 16 be N, P be a three-dimensional point on the slab plane 19, and the coordinates of the point in the coordinate system of the camera 15 be X1The coordinates in the coordinate system of the camera 16 are represented by X2The slab plane 19 can then be expressed as:
NTX2＝d
namely:
based on the rotation matrix R and translation vector T between the cameras 15 and 16, there are:
X1＝RX2+T
then it can be obtained:
wherein H' is a homography matrix of the slab plane 19 between the camera 15 coordinate system and the camera 16 coordinate system.
For the convenience of processing, it is necessary to further find a homography matrix H between the two images using H'.
Let x1Is the coordinate of P on the region 1 image, x2Is the coordinate of P on the image of the area 2, based on the internal reference matrix K of the camera 151And the reference matrix K of the camera 162The method comprises the following steps:
x1＝K1X1
x2＝K2X2
then it can be obtained:
namely:
therefore, the homography matrix H between the region 1 image and the region 2 image is obtained as follows:
and step S1334, converting the coordinates of the line-structured light spot set on the image of the area 2 into the coordinate system of the image of the area 1 based on the homography matrix between the image of the area 1 and the image of the area 2.
Specifically, the conversion of one point is, for example, as shown in the following equation:
wherein (u)1，v1,1)TFor a point in the region 1 image coordinate system, (u)2，v2,1)TFor the pixels in the region 2 image coordinate system, H is the homography between the region 1 image and the region 2 image, and the pixels in the region 2 image can be converted to the region 1 image by the formula.
And then, executing step S134, and connecting the two end points of the edge point set in the vertical direction of the continuous casting billet into a first straight line when the quantity of the line structured light on the image is enough. And S135, connecting two end points of the edge point set of the continuous casting slab in the horizontal direction into a second straight line. And S136, the intersection point of the first straight line and the second straight line is the angular point of the continuous casting slab.
And S14, extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting blank edge point coordinates based on the line structure light center line point set.
Specifically, the processing mode is basically the same as that of the angular point of the continuous casting billet, and the difference is that only the coordinate value is needed to divide the line structure light edge point set into a left point set and a right point set, so that the line structure light central line point set in the vertical direction is extracted, and the head and tail pixel point coordinates of each central line are taken out, namely the continuous casting billet edge point coordinates. The prior art has higher operation difficulty and lower efficiency in a severe production environment. Compared with the existing manual positioning method, the method has the advantages of simple operation, accurate positioning, convenient equipment maintenance and the like, and provides essential help for subsequent production, processing, detection and other links of the continuous casting billet.
Specifically, a set of pictures was taken for testing. After the group of pictures are processed, structured light sub-pixel edge extraction, center line extraction and continuous casting corner and edge point positioning are performed, so that a horizontal and vertical center line extraction process effect graph shown in fig. 1d can be obtained, details are shown as 1e, wherein a black line with a bright middle is a center line, a vertical center line extraction effect graph shown in fig. 1f is shown, and a continuous casting corner and edge contour point positioning effect graph shown in fig. 1g is shown. It can be seen that the algorithm can accurately position the corner points and the edge contour points of the continuous casting slab.
As shown in fig. 2, in an embodiment, the system for positioning corner points and edge contour point sets of a continuous casting slab of the present invention includes a shooting module 21, a preprocessing module 22, a first extraction module 23, and a second extraction module 24; the shooting module is used for shooting images of continuous casting billets and carrying out pretreatment to obtain images of a multi-line structured light point set; the preprocessing module is used for processing the images of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set; the first extraction module is used for extracting the central line end point of the line structure light edge point set to obtain a continuous casting blank horizontal direction edge point set and a continuous casting blank vertical direction edge point set, and obtaining a continuous casting blank angular point based on the continuous casting blank horizontal direction edge point set and the continuous casting blank vertical direction edge point set; the second extraction module is used for extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting blank edge point coordinates based on the line structure light center line point set.
It should be noted that: the structures and principles of the shooting module 21, the preprocessing module 22, the first extraction module 23 and the second extraction module 24 correspond to the steps in the continuous casting corner point and edge contour point set positioning method one by one, and therefore, the description is omitted here.
It should be noted that the division of the modules of the above system is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, a module may be a processing element that is set up separately, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes a function of the module. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Specific Integrated circuits (ASICs), or one or more Microprocessors (MPUs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
In an embodiment of the present invention, the present invention further includes a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any of the above methods for positioning corner points and edge contour point sets of a continuous casting slab.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
As shown in fig. 3, in an embodiment, the device for positioning corner points and edge contour point sets of a continuous casting slab of the present invention comprises: a processor 31 and a memory 32; the memory 32 is for storing a computer program; the processor 31 is connected to the memory 32 and configured to execute a computer program stored in the memory 32, so that the device for positioning sets of corner points and edge contours of a continuous casting slab executes any one of the methods for positioning sets of corner points and edge contours of a continuous casting slab.
Specifically, the memory 32 includes: various media that can store program codes, such as ROM, RAM, magnetic disk, U-disk, memory card, or optical disk.
Preferably, the Processor 31 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components.
In summary, the method, the system, the medium and the device for positioning the continuous casting corner point and the edge contour point set are used for realizing the non-contact automatic positioning of the continuous casting corner point and the edge contour point. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A continuous casting corner and edge contour point set positioning method is characterized by comprising the following steps:
shooting a continuous casting billet image and preprocessing the continuous casting billet image to obtain a multi-line structured light point set image;
processing the images of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set;
acquiring a continuous casting billet horizontal direction edge point set and a continuous casting billet vertical direction edge point set by extracting a central line end point of the line structure light edge point set based on the line structure light edge point set, and acquiring a continuous casting billet angular point based on the continuous casting billet horizontal direction edge point set and the continuous casting billet vertical direction edge point set;
and extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting billet edge point coordinates based on the line structure light center line point set.
2. The method for positioning corner points and edge contour point sets of a continuous casting slab as claimed in claim 1, wherein the step of shooting the continuous casting slab image and preprocessing the continuous casting slab image to obtain the light spot set image with the multi-line structure comprises:
projecting the multi-line structured light onto a continuous casting billet to shoot a first continuous casting billet image containing the multi-line structured light, and not projecting the multi-line structured light to shoot a second continuous casting billet image; and performing difference processing on the first continuous casting blank image and the second continuous casting blank image to obtain a multi-line structured light point set image.
3. The method for positioning corner points and edge contour point sets of a continuous casting slab as claimed in claim 1, wherein the step of processing the image of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set comprises:
performing line structure light edge extraction on the line structure light point set image based on a preset sub-pixel algorithm to obtain an edge discrete point set;
screening connecting lines according to the pixel distance and the division range in the horizontal and vertical directions to obtain a line set;
and sequencing the screened line set according to the coordinate values to obtain a line structured light edge point set.
4. The method according to claim 1, wherein the sets of corner points and edge contour points are obtained by extracting the center line end points of the sets of line-structured light edge points to obtain sets of slab-horizontal edge points and slab-vertical edge points,
obtaining a continuous casting angular point based on the continuous casting horizontal direction edge point set and the continuous casting vertical direction edge point set comprises:
acquiring a middle value of a coordinate in the vertical direction based on the linear structure light edge point set to obtain a central line of the linear structure light in the horizontal direction, and acquiring an end point of the central line of the linear structure light in the horizontal direction to become a continuous casting blank vertical direction edge point set;
acquiring a horizontal coordinate intermediate value based on the linear structure light edge point set to obtain a central line of linear structure light in a vertical direction, and acquiring an end point of the central line of the linear structure light in the vertical direction to become a continuous casting billet horizontal direction edge point set;
when the angular points of the continuous casting billets cannot be positioned due to insufficient quantity of line structure light on the images, coordinate conversion is carried out by utilizing a homography matrix, so that at least two line structure light in the horizontal and vertical directions in the images are on the continuous casting billets;
when the quantity of the line structured light on the image is enough, connecting two end points of the edge point set in the vertical direction of the continuous casting billet into a first straight line;
connecting two end points of the edge point set of the continuous casting blank in the horizontal direction into a second straight line;
and the intersection point of the first straight line and the second straight line is the angular point of the continuous casting billet.
5. A continuous casting corner and edge contour point set positioning system is characterized by comprising: the device comprises a shooting module, a preprocessing module, a first extraction module and a second extraction module;
the shooting module is used for shooting images of continuous casting billets and carrying out pretreatment to obtain images of a multi-line structured light point set;
the preprocessing module is used for processing the images of the multi-line structured light point set based on a preset algorithm to obtain a line structured light edge point set;
the first extraction module is used for extracting the central line end point of the line structure light edge point set to obtain a continuous casting blank horizontal direction edge point set and a continuous casting blank vertical direction edge point set, and obtaining a continuous casting blank angular point based on the continuous casting blank horizontal direction edge point set and the continuous casting blank vertical direction edge point set;
the second extraction module is used for extracting a line structure light center line point set in the vertical direction based on the line structure light edge point set, and obtaining continuous casting blank edge point coordinates based on the line structure light center line point set.
6. The system for positioning corner points and edge contour point sets of a continuous casting slab as claimed in claim 5, wherein the module for capturing an image of a continuous casting slab and performing a preprocessing to obtain an image of a light point set of a multi-line structure comprises:
projecting the multi-line structured light onto a continuous casting billet to shoot a first continuous casting billet image containing the multi-line structured light, and not projecting the multi-line structured light to shoot a second continuous casting billet image; and performing difference processing on the first continuous casting blank image and the second continuous casting blank image to obtain a multi-line structured light point set image.
7. The system of claim 5, wherein the preprocessing module is configured to process the image of the multi-line structured light point set to obtain a line structured light edge point set based on a preset algorithm, and comprises:
performing line structure light edge extraction on the line structure light point set image based on a preset sub-pixel algorithm to obtain an edge discrete point set;
screening connecting lines according to the pixel distance and the division range in the horizontal and vertical directions to obtain a line set;
and sequencing the screened line set according to the coordinate values to obtain a line structured light edge point set.
8. The system of claim 5, wherein the first extraction module is configured to obtain a continuous casting corner point and an edge point set in a horizontal direction and a vertical direction by extraction based on the line structured light edge point set, and the obtaining of the continuous casting corner point based on the continuous casting corner point and the edge point set in the vertical direction comprises:
acquiring a middle value of a coordinate in the vertical direction based on the linear structure light edge point set to obtain a central line of the linear structure light in the horizontal direction, and acquiring an end point of the central line of the linear structure light in the horizontal direction to become a continuous casting blank vertical direction edge point set;
acquiring a horizontal coordinate intermediate value based on the linear structure light edge point set to obtain a central line of linear structure light in a vertical direction, and acquiring an end point of the central line of the linear structure light in the vertical direction to become a continuous casting billet horizontal direction edge point set;
when the angular points of the continuous casting billets cannot be positioned due to insufficient quantity of line structure light on the images, coordinate conversion is carried out by utilizing a homography matrix, so that at least two line structure light in the horizontal and vertical directions in the images are on the continuous casting billets;
when the quantity of the line structured light on the image is enough, connecting two end points of the edge point set in the vertical direction of the continuous casting billet into a first straight line;
connecting two end points of the edge point set of the continuous casting blank in the horizontal direction into a second straight line;
and the intersection point of the first straight line and the second straight line is the angular point of the continuous casting billet.
9. A computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method for locating a set of corner and edge contour points of a slab as claimed in any one of claims 1 to 4.
10. The utility model provides a continuous casting billet angular point and edge profile point set positioner which characterized in that includes: a processor and a memory;
the memory is used for storing a computer program;
the processor is connected with the memory and is used for executing the computer program stored in the memory so as to enable the continuous casting corner point and edge contour point set positioning device to execute the continuous casting corner point and edge contour point set positioning method in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110625271.6A CN113222986B (en) | 2021-06-04 | 2021-06-04 | Continuous casting billet angular point and edge contour point set positioning method, system, medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110625271.6A CN113222986B (en) | 2021-06-04 | 2021-06-04 | Continuous casting billet angular point and edge contour point set positioning method, system, medium and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113222986A true CN113222986A (en) | 2021-08-06 |
| CN113222986B CN113222986B (en) | 2022-08-09 |
Family
ID=77082855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110625271.6A Active CN113222986B (en) | 2021-06-04 | 2021-06-04 | Continuous casting billet angular point and edge contour point set positioning method, system, medium and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113222986B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101839690A (en) * | 2010-04-13 | 2010-09-22 | 河海大学常州校区 | Visual inspection method for chip electronic component position error based on edge fitting |
| US20120250112A1 (en) * | 2011-03-31 | 2012-10-04 | Panasonic Corporation | Image processing apparatus and document scanning system having the same |
| CN105069799A (en) * | 2015-08-13 | 2015-11-18 | 深圳市华汉伟业科技有限公司 | Angular point positioning method and apparatus |
| CN106485275A (en) * | 2016-10-10 | 2017-03-08 | 厦门理工学院 | A kind of cover-plate glass of realizing positions, with liquid crystal display screen, the method fitted |
| CN107341802A (en) * | 2017-07-19 | 2017-11-10 | 无锡信捷电气股份有限公司 | It is a kind of based on curvature and the compound angular-point sub-pixel localization method of gray scale |
| CN110068270A (en) * | 2019-04-18 | 2019-07-30 | 上海拓今智能科技有限公司 | A kind of monocular vision box volume measurement method based on multi-line structured light image recognition |
| CN111951334A (en) * | 2020-08-04 | 2020-11-17 | 郑州轻工业大学 | Identification and positioning method and lifting method for stacking steel billets based on binocular vision technology |
| CN112365539A (en) * | 2020-11-11 | 2021-02-12 | 中南大学 | Ingot casting mold metal solution boundary positioning method integrating template matching and symmetrical straight line segmentation |
-
2021
- 2021-06-04 CN CN202110625271.6A patent/CN113222986B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101839690A (en) * | 2010-04-13 | 2010-09-22 | 河海大学常州校区 | Visual inspection method for chip electronic component position error based on edge fitting |
| US20120250112A1 (en) * | 2011-03-31 | 2012-10-04 | Panasonic Corporation | Image processing apparatus and document scanning system having the same |
| CN105069799A (en) * | 2015-08-13 | 2015-11-18 | 深圳市华汉伟业科技有限公司 | Angular point positioning method and apparatus |
| CN106485275A (en) * | 2016-10-10 | 2017-03-08 | 厦门理工学院 | A kind of cover-plate glass of realizing positions, with liquid crystal display screen, the method fitted |
| CN107341802A (en) * | 2017-07-19 | 2017-11-10 | 无锡信捷电气股份有限公司 | It is a kind of based on curvature and the compound angular-point sub-pixel localization method of gray scale |
| CN110068270A (en) * | 2019-04-18 | 2019-07-30 | 上海拓今智能科技有限公司 | A kind of monocular vision box volume measurement method based on multi-line structured light image recognition |
| CN111951334A (en) * | 2020-08-04 | 2020-11-17 | 郑州轻工业大学 | Identification and positioning method and lifting method for stacking steel billets based on binocular vision technology |
| CN112365539A (en) * | 2020-11-11 | 2021-02-12 | 中南大学 | Ingot casting mold metal solution boundary positioning method integrating template matching and symmetrical straight line segmentation |
Non-Patent Citations (2)
| Title |
|---|
| Y. -J. JEON ET AL.: "Defect detection algorithm for corner cracks in steel billet using discrete wavelet transform", 《2009 ICCAS-SICE》 * |
| 王崇岳 等: ".基于结构光图像法和阈值法的连铸坯定重剪切方法", 《中国科技信息》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113222986B (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243032B (en) | Full-automatic detection method for checkerboard corner points | |
| CN107844750B (en) | Water surface panoramic image target detection and identification method | |
| WO2018120038A1 (en) | Method and device for target detection | |
| JP7133283B2 (en) | Systems and methods for efficiently scoring probes in images with a vision system | |
| CN109784250B (en) | Positioning method and device of automatic guide trolley | |
| CN109034017A (en) | Head pose estimation method and machine readable storage medium | |
| CN112233181A (en) | 6D pose recognition method and device and computer storage medium | |
| CN114897864B (en) | Workpiece detection and defect judgment method based on digital-analog information | |
| CN107895375A (en) | The complicated Road extracting method of view-based access control model multiple features | |
| CN112163995A (en) | Splicing generation method and device for oversized aerial photographing strip images | |
| CN106780309A (en) | A kind of diameter radar image joining method | |
| CN107680035B (en) | Parameter calibration method and device, server and readable storage medium | |
| CN114037992A (en) | Instrument reading identification method and device, electronic equipment and storage medium | |
| CN110909772B (en) | High-precision real-time multi-scale dial pointer detection method and system | |
| CN111354047B (en) | Computer vision-based camera module positioning method and system | |
| CN113313116A (en) | Vision-based accurate detection and positioning method for underwater artificial target | |
| CN117496401A (en) | Full-automatic identification and tracking method for oval target points of video measurement image sequences | |
| CN113222986B (en) | Continuous casting billet angular point and edge contour point set positioning method, system, medium and device | |
| CN111178210B (en) | Image identification and alignment method for cross mark | |
| CN110751690B (en) | Visual positioning method for milling machine tool bit | |
| CN117611525A (en) | Visual detection method and system for abrasion of pantograph slide plate | |
| CN110458951B (en) | Modeling data acquisition method and related device for power grid pole tower | |
| CN110956664A (en) | Real-time camera position repositioning method for handheld three-dimensional scanning system | |
| CN115587943B (en) | Denoising method and device for point cloud data, electronic equipment and storage medium | |
| CN116402904A (en) | Combined calibration method based on laser radar inter-camera and monocular camera |
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 |