CN117911419A - Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment - Google Patents
Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment Download PDFInfo
- Publication number
- CN117911419A CN117911419A CN202410317919.7A CN202410317919A CN117911419A CN 117911419 A CN117911419 A CN 117911419A CN 202410317919 A CN202410317919 A CN 202410317919A CN 117911419 A CN117911419 A CN 117911419A
- Authority
- CN
- China
- Prior art keywords
- image
- billet
- fitting
- determining
- foreground
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 229910000831 Steel Inorganic materials 0.000 title claims description 84
- 239000010959 steel Substances 0.000 title claims description 84
- 238000004891 communication Methods 0.000 claims abstract description 74
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000005096 rolling process Methods 0.000 claims abstract description 19
- 238000012937 correction Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 40
- 238000003860 storage Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000011426 transformation method Methods 0.000 claims description 6
- 230000003014 reinforcing effect Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000010191 image analysis Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 21
- 238000005516 engineering process Methods 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 8
- 230000007797 corrosion Effects 0.000 description 6
- 238000005260 corrosion Methods 0.000 description 6
- 238000003708 edge detection Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000002834 transmittance Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000009749 continuous casting Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The application relates to the field of rolling image analysis, and discloses a method and a device for detecting steel-turning angle enhancement of a medium plate, a medium and equipment. The method comprises the following steps: shooting a billet image by a target camera, and carrying out distortion correction on the billet image according to camera parameters; sequentially performing defogging treatment and contrast enhancement treatment on the billet image; based on the gray scale of each pixel point in the billet image, a foreground area and a background area are identified, and holes in the foreground area are filled; performing image morphology opening operation on the billet image; determining a target communication area based on the communication relation of the foreground area, and fitting the edge contour of the target communication area; fitting a circumscribed minimum rectangle corresponding to the target communication area according to the edge profile, and determining the angle of the billet according to the offset angle of the rectangle relative to the preset reference direction. The method solves the problems that the image of the existing method has the defects of blurring, noise and the like, and a stable angle detection result cannot be obtained.
Description
Technical Field
The application relates to the field of rolling image analysis, in particular to a method and a device for detecting steel rotation angle enhancement of a medium plate, a medium and equipment.
Background
According to the regulations of the current national standard GB 709-2006 of hot rolled steel plate and steel strip size, shape, weight and allowable deviation, the classification of the hot rolled steel plate can be classified according to three modes of thickness deviation classification, thickness grading classification, hot rolled steel plate size range and the like. Conventionally, steel sheets are classified into medium-thickness plates, thick plates, and extra-thick plates according to thickness, and steel sheets having a thickness of 4 to 20mm are generally called medium-thickness plates. In the rolling production of medium plates, the steel conversion operation is an important link, modern medium plate production lines with fine equipment, complete process and high degree of automation are built in steel factories in China nowadays, and the steel conversion operation is automatically controlled except in a rolling area. The steel transferring operation becomes the only bottleneck of full-automatic control of the medium plate rolling area.
The detection algorithm of the angle of the steel billet in the steel turning process is a precondition for realizing automatic control of steel turning, the traditional manual steel turning operation mainly carries out steel billet detection by visual observation, and the mode is too dependent on the working experience of operators, and is lower in efficiency and accuracy. With the development of intelligent technology, the machine vision recognition technology is widely applied to the industrial field at present, has the advantages of high processing speed, high detection precision, easy integration and the like, and is widely applied to steelmaking, continuous casting and rolling procedures in the domestic steel industry.
However, in the actual production process, due to the problems of temperature change of the steel billet, dephosphorization of high-pressure water, uneven distribution of water vapor and gray scale on the surface of the steel billet caused by a roller body cooling system, and the like, the acquired image inevitably has the defects of blurring, noise and the like, the image quality is seriously affected, and a stable angle detection result cannot be obtained.
Disclosure of Invention
In view of the above, the application provides a method, a device, a medium and equipment for detecting the steel-turning angle enhancement of a medium plate, which solve the problems that the image of the existing method has the defects of blurring, noise point and the like and a stable angle detection result cannot be obtained.
According to one aspect of the application, there is provided a method for detecting the steel rotation angle enhancement of a medium plate, comprising:
shooting a billet image through a target camera in a steel turning link of the medium plate rolling, and carrying out distortion correction on the billet image according to camera parameters of the target camera;
sequentially performing defogging treatment and contrast enhancement treatment on the distortion corrected billet image;
Recognizing a foreground region and a background region based on the gray scale of each pixel point in the billet image after the contrast enhancement processing, and filling holes in the foreground region;
performing image morphology opening operation on the billet image filled with the holes;
determining a target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area;
Fitting an circumscribed minimum rectangle corresponding to the target communication area according to the edge profile, and determining a billet angle according to the offset angle of the rectangle relative to a preset reference direction.
Optionally, the defogging process and the contrast enhancement process are sequentially performed on the distortion-corrected billet image, including:
determining an atmospheric light component corresponding to the distortion-corrected billet image, determining the perspective of each pixel point in the distortion-corrected billet image according to the atmospheric light component, and performing defogging treatment on the distortion-corrected billet image according to the atmospheric light component and the perspective;
And stretching the gray value of each pixel point in the defogging-treated billet image by a linear transformation method to obtain the billet image after the contrast enhancement treatment.
Optionally, the identifying the foreground area and the background area based on the gray scale of each pixel point in the billet image after the contrast enhancement processing, and filling the holes in the foreground area includes:
Calculating the average gray value of each local window in the billet image after the contrast enhancement treatment, and respectively calculating the deviation between the gray value of each pixel to be identified in the billet image after the contrast enhancement treatment and the average gray value;
If the deviation is larger than a deviation threshold, determining the pixel point to be identified as a foreground pixel point, otherwise, determining the pixel point to be identified as a background pixel point;
determining the foreground region according to the foreground pixel points, and scanning the background pixel points in the foreground region;
and determining holes in the foreground region based on the scanning result, and filling the holes.
Optionally, the determining the target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area includes:
traversing the pixel points in the foreground region, and determining the at least one connected region based on the adjacency relation of each pixel point;
Determining one communication area as the target communication area according to the area and the rectangular degree of each communication area;
fitting an edge curve of the target communication area by using a three-point interpolation method to obtain a contour point set corresponding to the target communication area.
Optionally, the fitting, according to the edge profile, a circumscribed minimum rectangle corresponding to the target communication area includes:
Preprocessing the contour point set, and performing initial fitting on the preprocessed contour point set by using a least square fitting method to obtain a fitting rectangle;
calculating residual errors from each contour point in the preprocessed contour point set to the fitting rectangle respectively, and weighting the residual errors;
and fitting again according to the weighted residual errors to obtain new fitted rectangles, returning to the step of respectively calculating the residual errors from each contour point in the preprocessed contour point set to the fitted rectangles until the preset iteration termination condition is reached, and determining the current fitted rectangle as the circumscribed minimum rectangle.
Optionally, the weight corresponding to the residual is inversely related to the residual.
Optionally, before the distortion correction of the billet image according to the camera parameters of the target camera, the method includes:
And shooting a plurality of calibration plate pictures with different angles by using the target camera, and calibrating the target camera based on the calibration plate pictures to obtain camera parameters, wherein the camera parameters comprise internal parameters, external parameters and distortion parameters.
According to another aspect of the present application, there is provided a device for detecting steel turning angle enhancement of a medium plate, the device comprising:
The image shooting module is used for shooting a steel billet image through a target camera in a steel turning link of the medium plate rolling, and carrying out distortion correction on the steel billet image according to camera parameters of the target camera;
The image processing module is used for sequentially carrying out defogging processing and contrast enhancement processing on the distortion corrected billet image; and identifying a foreground region and a background region based on the gray scale of each pixel point in the billet image after the contrast enhancement, and filling holes in the foreground region; and performing image morphology opening operation on the billet image after hole filling; determining a target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area;
And the angle detection module is used for fitting the circumscribed minimum rectangle corresponding to the target communication area according to the edge profile and determining the angle of the billet according to the offset angle of the rectangle relative to the preset reference direction.
Optionally, the image processing module is configured to:
determining an atmospheric light component corresponding to the distortion-corrected billet image, determining the perspective of each pixel point in the distortion-corrected billet image according to the atmospheric light component, and performing defogging treatment on the distortion-corrected billet image according to the atmospheric light component and the perspective;
And stretching the gray value of each pixel point in the defogging-treated billet image by a linear transformation method to obtain the billet image after the contrast enhancement treatment.
Optionally, the image processing module is configured to:
Calculating the average gray value of each local window in the billet image after the contrast enhancement treatment, and respectively calculating the deviation between the gray value of each pixel to be identified in the billet image after the contrast enhancement treatment and the average gray value;
If the deviation is larger than a deviation threshold, determining the pixel point to be identified as a foreground pixel point, otherwise, determining the pixel point to be identified as a background pixel point;
determining the foreground region according to the foreground pixel points, and scanning the background pixel points in the foreground region;
and determining holes in the foreground region based on the scanning result, and filling the holes.
Optionally, the image processing module is configured to:
traversing the pixel points in the foreground region, and determining the at least one connected region based on the adjacency relation of each pixel point;
Determining one communication area as the target communication area according to the area and the rectangular degree of each communication area;
fitting an edge curve of the target communication area by using a three-point interpolation method to obtain a contour point set corresponding to the target communication area.
Optionally, the angle detection module is configured to:
Preprocessing the contour point set, and performing initial fitting on the preprocessed contour point set by using a least square fitting method to obtain a fitting rectangle;
calculating residual errors from each contour point in the preprocessed contour point set to the fitting rectangle respectively, and weighting the residual errors;
and fitting again according to the weighted residual errors to obtain new fitted rectangles, returning to the step of respectively calculating the residual errors from each contour point in the preprocessed contour point set to the fitted rectangles until the preset iteration termination condition is reached, and determining the current fitted rectangle as the circumscribed minimum rectangle.
Optionally, the weight corresponding to the residual is inversely related to the residual.
Optionally, the apparatus further comprises a camera parameter acquisition module for:
And shooting a plurality of calibration plate pictures with different angles by using the target camera, and calibrating the target camera based on the calibration plate pictures to obtain camera parameters, wherein the camera parameters comprise internal parameters, external parameters and distortion parameters.
According to still another aspect of the present application, there is provided a medium having stored thereon a program or instructions which, when executed by a processor, implements the above-described medium plate steel angle reinforcing detection method.
According to still another aspect of the present application, there is provided an apparatus comprising a storage medium storing a computer program and a processor implementing the above method for detecting steel turning angle enhancement of a medium plate when the processor executes the computer program.
By means of the technical scheme, the steel billet real-time image is collected based on the machine vision technology, and the steel billet angle detection enhancement algorithm based on the machine vision technology is developed based on camera calibration and distortion correction, image defogging processing, gray level linear transformation, dynamic threshold segmentation, filling, opening operation, feature screening, sub-pixel edge detection and external minimum rectangular fitting, so that the steel billet angle can be extracted in real time before and after the machine vision technology, complex environment changes in the production process can be adapted, and real-time and stable angle detection feedback values are provided for an automatic steel conversion control system.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 shows a schematic flow chart of a method for detecting steel turning angle enhancement of a medium plate, which is provided by the embodiment of the application;
FIG. 2 shows a schematic flow chart of another method for detecting steel turning angle enhancement of a medium plate according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of another method for detecting the steel rotation angle enhancement of a medium plate according to an embodiment of the present application;
FIG. 4 is a schematic flow chart of another method for detecting the steel rotation angle enhancement of a medium plate according to an embodiment of the present application;
Fig. 5 is a schematic flow chart of a method for detecting steel rotation angle enhancement of a fifth medium plate according to an embodiment of the present application;
FIG. 6 is a schematic flow chart of a sixth method for detecting steel rotation angle enhancement of a medium plate according to an embodiment of the present application;
fig. 7 is a schematic flow chart of a seventh method for detecting steel rotation angle enhancement of a medium plate according to an embodiment of the present application;
FIG. 8 illustrates a dynamic threshold segmentation schematic provided by an embodiment of the present application;
FIG. 9 illustrates a schematic filling diagram provided by an embodiment of the present application;
FIG. 10 illustrates a schematic diagram of an opening operation provided by an embodiment of the present application;
FIG. 11 is a schematic diagram of sub-pixel level edge detection according to an embodiment of the present application;
FIG. 12 is a schematic illustration of an circumscribed minimum matrix fit provided by an embodiment of the present application;
fig. 13 shows a real-time angle schematic diagram of a steel billet according to an embodiment of the present application;
fig. 14 shows a block diagram of a device for detecting steel rotation angle enhancement of a medium plate according to an embodiment of the present application.
Detailed Description
The application will be described in detail hereinafter with reference to the drawings in conjunction with embodiments. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
In this embodiment, a method for detecting the steel rotation angle of a medium plate is provided, specifically, a method for detecting the steel rotation angle of a medium plate, as shown in fig. 1, includes:
and 101, shooting a billet image through a target camera in a steel turning link of the medium plate rolling, and carrying out distortion correction on the billet image according to camera parameters of the target camera.
Specifically, rolling refers to a process of rolling and pressing metal through a pair of rollers, and a steel turning link is an important link in the rolling process, and refers to a process of rotating a metal plate between different rolling directions and positions. The method for detecting the steel turning angle enhancement of the medium plate is used for analyzing the billet image acquired by the target camera in real time in the steel turning link of the medium plate rolling to obtain the billet angle so as to maintain the correct rolling direction and position in the subsequent rolling process and realize the automatic control of the steel turning operation of the medium plate.
In this step, since the position of the target camera may not be parallel to the billet, the shot billet image is distorted, so as to affect the accurate measurement of the billet angle, therefore, the pixel coordinates in the billet image are recalculated according to the camera parameters such as distortion parameters, and the distortion correction is performed on the image, so as to eliminate the influence caused by the distortion.
Step 102, defogging processing and contrast enhancement processing are sequentially carried out on the billet image after distortion correction.
In the step, as the atmospheric scattering can cause the blurring of the billet image and reduce the image quality, defogging treatment can be carried out on the billet image after distortion correction, so that the image is clearer, the details are clearer, and further, a more accurate angle detection result is obtained. For example, details of the image may be restored by analyzing the haze level in the image, specifically, based on an atmospheric light model, utilizing the effect of haze on the brightness and contrast of the billet image, and removing haze through transmittance estimation. After defogging treatment, contrast enhancement treatment can be performed, and by improving the contrast of the billet image, the position with high brightness is brighter and the position with low brightness is darker, so that the position where the billet is can be conveniently segmented.
And 103, identifying a foreground area and a background area based on the gray scale of each pixel point in the billet image after the contrast enhancement processing, and filling holes in the foreground area.
In this step, a foreground region with higher brightness and a background region with lower brightness are identified in the image according to the gray scale of each pixel point in the billet image after the contrast enhancement processing, that is, according to the brightness of different positions in the billet image after the contrast enhancement processing, and the position corresponding to the billet is in the foreground region. In addition, as the foreground region may have some dark pixels, the holes in the foreground region are further filled to obtain a more complete foreground region.
And 104, performing image morphology opening operation on the billet image after hole filling.
In this step, the billet image after the contrast enhancement processing is subjected to an open operation by a first erosion operation and then a dilation operation. The corrosion is to slide the rectangular structure kernel through the image, and the intersection obtained by comparing the pixel points corresponding to the binary image with the pixels of the structural elements is the corroded image pixel. The individual billet elements are interconnected and separated from the background elements by a corrosion operation while eliminating small blocks of noise objects in the background region. The expansion is to slide the inner core of the rectangular structure through the image, compare the pixel points of the binary image with the pixel points of the corresponding structural elements, and the union obtained after the comparison is the expanded image pixel. The image pixel gaps left by excessive erosion in the erosion operation are filled by expansion. The method can remove isolated and tiny points and rough edge lines through opening operation, eliminate connection of burrs and stenosis, and retain the original area of most areas, and the calculation formula of the opening operation is as follows: . In the method, in the process of the invention, Representing an open operation on A with structural element B,Indicating that A is corroded by B,RepresentationIs inflated by B.
And 105, determining a target communication area based on the communication relation of the foreground areas in the billet image after the opening operation, and fitting the edge contour of the target communication area.
In this step, considering that there may be two foreground regions connected in a diagonal direction, the two discrete foreground regions should be connected in series, so in the billet image after the opening operation, the communicating region is scanned based on the neighborhood of each pixel point in the foreground region, so as to obtain a target communicating region corresponding to the billet, and the edge contour of the target communicating region is fitted, so that the contour of the billet can be obtained.
And 106, fitting a circumscribed minimum rectangle corresponding to the target communication area according to the edge profile, and determining the angle of the billet according to the offset angle of the rectangle relative to the preset reference direction.
In this step, since the target communication region obtained in the foregoing step may be irregularly shaped, and the billet is generally rectangular, the smallest rectangular shape that can contain the target communication region is obtained by fitting the circumscribed smallest rectangle. At this time, the offset angle of the rectangle with respect to the preset reference direction is the billet angle.
The embodiment is based on a machine vision technology, acquires real-time images of billets, and based on camera calibration and distortion correction, image defogging processing, gray level linear transformation, dynamic threshold segmentation, filling, opening operation, feature screening, sub-pixel edge detection and external minimum rectangular fitting, develops a billet angle detection enhancement algorithm in a steel conversion process based on the machine vision technology, can realize real-time extraction of billet angles before and after the machine, can adapt to complex environmental changes in the production process, and provides real-time and stable angle detection feedback values for an automatic steel conversion control system.
Further, as a refinement and expansion of the specific implementation of the above embodiment, for fully explaining the specific implementation process of the embodiment, another method for detecting the steel rotation angle enhancement of a medium plate is provided, which further defines the content of "sequentially performing defogging treatment and contrast enhancement treatment on a billet image after distortion correction", as shown in fig. 2, and includes the following steps:
Step 201, determining an atmospheric light component corresponding to the distortion-corrected billet image, determining the perspective of each pixel point in the distortion-corrected billet image according to the atmospheric light component, and performing defogging treatment on the distortion-corrected billet image according to the atmospheric light component and the perspective;
And 202, stretching the gray value of each pixel point in the defogging billet image by a linear transformation method to obtain the billet image after the contrast enhancement treatment.
In this embodiment, defogging is performed first using an atmospheric scattering model, which can be used for image defogging in the machine vision field, by the formula. WhereinRepresenting hazy images,Representing haze-free images,For transmittance, a represents a global atmospheric light value.
In a specific application process, firstly, selecting the minimum pixel value in three RGB channels as a gray value for each pixel point in the distortion corrected billet image, and then performing rectangular morphological corrosion operation on a real image to generate a dark channel image. Wherein, the image morphology operation refers to a collection of a series of image processing operations based on a shape, and has four basic operations: corrosion, expansion, open operation, close operation, wherein corrosion is the removal of some burrs and details of an image, corrosion can generally be used to eliminate noise, separate image elements, etc., which is also a spatial filtering in nature.
It will be appreciated that in a foggy, non-pure white region, typically there is a very low pixel value of one of the three channels of RGB, close to 0, whereas in a foggy image, the dark channel region is much greater than 0, in gray. Therefore, in the generated dark channel image, the hazy area can be determined according to the brightness size of each pixel point. Based on this, after the dark channel image is generated, the brightest 0.1% pixel is extracted in accordance with the brightness level in the dark channel image, and the value of the point having the highest brightness at the corresponding position is found in the original hazy image as the atmospheric light value, that is, the atmospheric light component a.
From the atmospheric light component, the transmittance of each pixel is estimated in the original image. The calculation formula of the transmittance is:。
Wherein omega has a value of 0.95, A window centered at pixel x is shown.
When the transmittance t is smaller, J is larger, so that t is limited by a lower boundary t 0, which is 0.1, whenTime, letFinal haze free imageCan be expressed as follows:
Based on the formula, defogging treatment can be carried out on the billet image according to the perspective and the atmospheric light component, and the defogged image can be recovered.
After defogging treatment, the gray value of each pixel point can be changed by a linear transformation method so as to improve the light-dark contrast of the image. Wherein, the linear transformation formula is shown as follows: mult+add. In the/> Representing gray value before gray stretching operation of billet image,The gray value after gray stretching of the billet image is represented, mult represents a multiplier factor, and Add represents an addend factor. It can be understood that the gray values refer to the color depth in the black-and-white image, and the larger the color gray values are, the brighter the pixel points, so that the difference between the gray values is increased without changing the magnitude relation between the gray values of the pixel points, and the contrast of the image can be improved. This embodiment enables the contrast of the billet image to be pulled apart by selecting appropriate parameters, making the background portion darker and the billet portion brighter.
According to the embodiment, defogging treatment and contrast enhancement treatment are carried out on the steel billet image, so that the definition of the image is improved, the brightness difference between the steel billet part and the background part is larger, the steel billet part is more conveniently segmented in the image, and the problem that the detection accuracy of the steel billet angle is reduced due to the unclear image is solved.
Further, as a refinement and expansion of the specific implementation of the foregoing embodiment, for fully explaining the specific implementation process of the present embodiment, another method for detecting the steel rotation angle enhancement of a medium plate is provided, where the method further defines "based on the gray scale of each pixel point in the billet image after the contrast enhancement processing, the foreground area and the background area are identified, and the holes in the foreground area are filled", as shown in fig. 3, including the following steps:
step 301, calculating an average gray value of each local window in the billet image after the contrast enhancement processing, and calculating a deviation between the gray value and the average gray value of each pixel to be identified in the billet image after the contrast enhancement processing;
step 302, if the deviation is greater than the deviation threshold, determining the pixel to be identified as a foreground pixel, otherwise, determining the pixel to be identified as a background pixel;
step 303, determining a foreground region according to the foreground pixel points, and scanning the background pixel points in the foreground region;
step 304, determining holes in the foreground region based on the scan result, and filling the holes.
In this embodiment, the foreground and the background are recognized for the billet image after the contrast enhancement processing. The steel billet is shielded by water vapor, so that the surface brightness is different, and a proper threshold value can not be found for dividing the foreground and the background in the whole image. But in the local area there is a relatively sharp contrast of the foreground and the background, based on which this embodiment segments the region of interest, i.e. the foreground region, from the background gray value of the local area by using a dynamic threshold operator.
In the specific application process, the average value filtering is firstly used for carrying out smoothing treatment on the image, and the average gray value of the current window is obtained through calculation. This value is used as a background estimate for the local area. The contrast-enhanced billet image and the smoothed image are compared pixel by pixel, and the threshold value is dynamically determined by the deviation between the two. And dividing areas with a plurality of gray values higher than the gray of the smoothed image according to the dynamic threshold value. Specifically, if the deviation is greater than the deviation threshold, determining the pixel point to be identified as a foreground pixel point, otherwise, determining the pixel point to be identified as a background pixel point, and determining the foreground region according to the foreground pixel point. For example, the gray value of the pixel point in the original image is g0, in the corresponding local range, the gray value of the image after mean filtering smoothing is gt, the Offset is an Offset threshold, wherein the Offset threshold represents the acceptable range of the gray value deviation between the original image and the threshold image, and then the region meeting the condition that g0 is greater than or equal to gt+offset can be selected as the interested region, namely the foreground region.
After the foreground region is obtained, filling is carried out on background pixels in the foreground region, so that holes in the foreground region are avoided. Specifically, from a source region entered by a user, pixels within a foreground region are scanned in a particular order, such as from top to bottom, left to right. When one background pixel is scanned, all the background pixels connected with the background pixel are found by searching the connected domain from the point. And marking all the pixels in the searched connected domain as filling areas. And continuing to scan the next unviewed pixel, repeating the steps until the scanning of the whole foreground region is completed, and filling the foreground region after the dynamic threshold segmentation.
The embodiment sequentially performs operations of foreground (edge), threshold segmentation, background communication area removal and hole filling, segments an area possibly belonging to a steel billet in a steel billet image, further processes the area in a subsequent step, and detects the angle of the steel billet.
Further, as a refinement and extension of the specific implementation of the foregoing embodiment, in order to fully describe the specific implementation process of the embodiment, another method for detecting the steel rotation angle enhancement of a medium plate is provided, where the method further defines the content of "determining a target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area", as shown in fig. 4, including the following steps:
Step 401, traversing pixel points in a foreground region, and determining at least one connected region based on an adjacent relation of each pixel point;
Step 402, determining one communication area as a target communication area according to the area and the rectangular degree of each communication area;
and step 403, fitting an edge curve of the target communication area by using a three-point interpolation method to obtain a contour point set corresponding to the target communication area.
In this embodiment, the target connected region where the tapping blank is located is further screened in the foreground region first, specifically, the region is screened according to the area and the rectangle degree of the region first, the segmented region is traversed by using the 8-neighborhood adjacent relation, and pixels with the same connected relation are allocated to the same connected region. For each connected region, the pixel area is calculated by counting the number of pixels in the region. And sorting the stored connected areas according to the pixel areas, and selecting one target connected area from the connected areas according to the pixel areas to serve as a billet characteristic image. In addition, the pixel area and the rectangular degree of the area can be considered at the same time, so that the final target communication area can be obtained.
Then, the target connected region is subjected to curve fitting of edge contours, in particular, pixel-level edge pointsFitting an edge curve using three-point interpolation, taking three interpolation points/>, in the X direction，，The corresponding function value is、、. Similarly, three interpolation points/>, are taken in the Y direction，，The corresponding function value is、、. Substituting the interpolation points selected in X, Y directions into an interpolation formula to respectively obtain quadratic interpolation functions/>, in the X directionAnd quadratic interpolation function in Y directionThe expression is as follows:
the derivative of the quadratic curve is 0, namely the sub-pixel coordinate in X, Y directions, so that =0, Resulting in coordinatesLet=0, Resulting in coordinates. The specific expression is as follows:
And obtaining all the sub-pixel points at the edge positions and connecting the sub-pixel points after obtaining the coordinates of the sub-pixel points, so as to obtain the sub-pixel edge contour of the image.
According to the embodiment, the position of the billet is accurately found in the foreground area based on the communication relation of each pixel point, the sub-pixel level edge detection is utilized, the image is subjected to finer analysis on the basis of the pixel level, and more accurate edge position information is obtained, so that the subsequent image processing task can be more accurate and reliable.
Further, as a refinement and expansion of the specific implementation manner of the foregoing embodiment, for fully explaining the specific implementation process of the embodiment, another method for detecting the steel rotation angle enhancement of a medium plate is provided, where the method further defines the content of "fitting the circumscribed minimum rectangle corresponding to the target communication area according to the edge profile", as shown in fig. 5, and includes the following steps:
Step 501, preprocessing a contour point set, and performing initial fitting on the preprocessed contour point set by using a least square fitting method to obtain a fitting rectangle;
Step 502, calculating residual errors from each contour point in the preprocessed contour point set to the fitting rectangle, and weighting the residual errors;
step 503, fitting again according to the weighted residual errors to obtain new fitted rectangles, and returning to the step of respectively calculating the residual errors from each contour point in the preprocessed contour point set to the fitted rectangle until reaching the preset iteration termination condition, and determining that the current fitted rectangle is the circumscribed minimum rectangle.
In this embodiment, the circumscribed minimum rectangle corresponding to the target communication area is fitted, and then the billet angle is obtained according to the inclination angle of the rectangle. Specifically, the circumscribed minimum rectangle can be obtained by fitting according to the following steps: and preprocessing the input contour point set. The method comprises the data processing technologies of sorting data, removing abnormal values and the like, and aims to reduce the influence of the abnormal values on fitting results; performing initial fitting on the preprocessed contour point set by using a traditional least square fitting method; calculating the residual error from each contour point to the initial fitting rectangle, wherein the residual error represents the difference between each point and the fitting rectangle; weighting the residual errors by applying a Tukey weighting function; and re-fitting the rectangle according to the weighted residual error to obtain a more robust fitting result. This process requires multiple iterations to further optimize the fit results. In each iteration, the residual is recalculated according to the weighting function and the rectangle is fitted again. Until the final circumscribed minimum rectangle is obtained, the included angle between the long axis of the rectangle and the x axis is the billet angle.
The circumscribed minimum rectangle obtained by fitting the target communication area has certain robustness and stability, and has certain tolerance to the change, rotation or partial shielding of the shape of the target communication area. Compared with the outline of the target communication area, the minimum circumscribed rectangle is more stable and is not easily interfered by noise, incomplete edges or shape change. In addition, the shape of the minimum circumscribed rectangle is more regular, so that the position and the shape of the steel billet can be clearly identified, and the steel billet angle can be obtained more conveniently.
Further, as a refinement and extension of the foregoing embodiment, for fully explaining the implementation procedure of the embodiment, another method for detecting the steel rotation angle enhancement of the medium plate is provided, where the method further includes, before the step of "correcting distortion of the billet image according to the camera parameters of the target camera", the content of "obtaining the camera parameters", and as shown in fig. 6, the steps include:
And 601, shooting a plurality of calibration plate pictures with different angles by using a target camera, and calibrating the target camera based on the calibration plate pictures to obtain camera parameters, wherein the camera parameters comprise internal parameters, external parameters and distortion parameters.
In this embodiment, 20 calibration plate pictures with different angles are shot by a CCD (Charge Coupled Device ) camera installed above the roller way, and camera calibration is performed based on the calibration plate pictures, so that camera parameters, such as camera internal parameters, external parameters and distortion parameters, are obtained through calculation, and further the distortion correction can be performed on the billet image by using the camera parameters. The calibration plate can be a dot calibration plate, a checkerboard calibration plate and the like, and a Zhang Zhengyou calibration method can be adopted in the calibration process.
Fig. 7 shows a method for detecting the steel rotation angle enhancement of a medium plate according to another embodiment of the present application, as shown in the figure, the method includes the following steps:
Step 701, camera calibration and distortion correction.
In this step, camera parameter determination and distortion correction are performed using Zhang Zhengyou calibration methods, using a dot calibration plate as a calibration object. The dot calibration plate consists of a 7X 7 dot array and a square frame with a chamfer angle, the size of the calibration plate is 800mm X800 mm, the diameter of each dot is 50mm, the distance between adjacent dots is 100mm, each dot and the border are taken as characteristic reference points, and characteristic point data in 20 pictures are compared through a Zhang Zhengyou calibration method to correct internal and external parameters of the camera.
The calibration results are shown in tables 1-3 below:
Table 1 camera internal parameters
| Pixel width/μm | High pixel/μm | Focal length/mm | Center x coordinate/Pixel | Center y coordinate/Pixel | Image width/Pixel | Image height/Pixel |
| 8.29862 | 8.3 | 11.6503 | 359.379 | 235.82 | 659 | 494 |
Table 2 camera external parameters
| X-direction translation/mm | Translation in Y direction/mm | Z-direction translation/mm | Rotation in the X direction | Y-direction rotation/° | Z-direction rotation/° |
| 6.60547 | 1.93844 | 425.423 | 3.55931 | 354.219 | 180.613 |
Table 3 camera distortion coefficients
| K1(1/m2) | K2(1/m4) | K3(1/m6) | P1(1/m2) | P2(1/m2) |
| 0.2093 | -0.7269 | 0.2962 | 0.1316 | 0.0632 |
Step 702, image defogging processing.
In this step, a dark channel image is obtained, the transmittance and the atmospheric light component are calculated, and the raw image is defogged by substituting into an atmospheric scattering model.
In step 703, gray scale is linearly transformed.
In the step, the multiplier factor Mult is 5, the additive factor Add is-150, the pixel gray value below the gray value 80 can be reduced to 0, the pixel gray value above 80 is converted to 250, and the contrast ratio of the billet image is greatly improved.
Step 704, dynamic threshold segmentation.
In this step, the average filter mask width is set to 230 and the height is set to 230. The offset value offset in the dynamic threshold segmentation is 12, and the extraction mode is a light mode, namely, extracting an area of which the original image is brighter than the image subjected to mean value filtering by more than 12 gray scales. The picture after the processing by dynamic threshold segmentation is shown in fig. 8.
Step 705, filling.
In the step, the holes in the segmented regions are filled, so that the regions are more continuous and complete, and subsequent analysis and processing are facilitated. The picture after the filling process is shown in fig. 9.
Step 706, open operation.
The width of the rectangular structure core in the opening operation is set to 20 and the height is set to 20. The picture after processing by the on operation is shown in fig. 10.
Step 707, feature screening.
In this step, the steel billet is screened according to the basic area range and the rectangular degree, and the minimum value of the steel billet area is 18000 and the maximum value of the steel billet area is 400000 according to the actual production condition. The minimum value of the rectangle degree is 0.8, and the maximum value is 1.0. And sorting the selected connected domains according to the pixel areas according to the condition screening areas, and selecting the connected domain with the largest pixel area as the billet characteristic image.
At step 708, sub-pixel edge detection.
In this step, the sub-pixel coordinates are calculated using polynomial interpolation, and the picture processed by the sub-pixel edge detection algorithm is shown in fig. 11.
Step 709, circumscribes a minimum rectangle fit.
The least squares method finds a straight line by fitting data points. The basic principle is that the square sum error of the distances between all points and the fitting straight line is the smallest. The expression of the assumed straight line is: The sum of squares error is:
Under the condition that some edge noise is relatively large, the data contains a large number of noise points, and the traditional least square method cannot obtain an optimal result, so that the method adopts a least square method based on weighting for fitting. The straight line fitting of the added weight function considers the distance from different points to the straight line, reduces the fitting error and can improve the fitting precision. The weighting function based on the Tukey weighting function is defined as:
In the method, in the process of the invention, Representing the distance of a point to a straight line,Is a clipping coefficient representing the distance, which serves to determine the outlier. /(I)
When (when)When the value of the weighting function is 0, it means that a larger residual gives a smaller weight. WhenWhen the value of the weighting function varies with the distance in the (0, 1) interval, the smaller the distance from the point to the straight line is, the larger the value of the weighting function is, which means that the smaller residual is given a larger weight. Clipping coefficientAnd adaptively setting according to the standard deviation of the one-dimensional Gaussian distribution.
Under the condition of a weighted least square method, solving an expression with the minimum residual error as follows:
and when the residual error is minimum, obtaining the linear equation parameters.
Fitting based on Tukey weight functions can eliminate the influence of outliers, and a more accurate fitting result is obtained. The picture processed by the circumscribed minimum rectangle fitting algorithm is shown in fig. 12. The included angle (-89.45 deg.) between the long axis and the x axis of the rectangle is the real-time angle of the billet, as shown in fig. 13.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
Further, as a specific implementation of the method for detecting the steel rotation angle enhancement of the medium plate, an embodiment of the present application provides a device for detecting the steel rotation angle enhancement of the medium plate, as shown in fig. 14, where the device includes: image shooting module, image processing module and angle detection module, wherein:
The image shooting module is used for shooting a steel billet image through the target camera in a steel turning link of the medium plate rolling and carrying out distortion correction on the steel billet image according to camera parameters of the target camera;
the image processing module is used for sequentially carrying out defogging processing and contrast enhancement processing on the distortion corrected billet image; and identifying a foreground region and a background region based on the gray scale of each pixel point in the billet image after the contrast enhancement, and filling holes in the foreground region; and performing image morphology opening operation on the billet image after hole filling; determining a target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area;
the angle detection module is used for fitting the circumscribed minimum rectangle corresponding to the target communication area according to the edge profile, and determining the angle of the billet according to the offset angle of the rectangle relative to the preset reference direction.
Optionally, the image processing module is configured to:
Determining an atmospheric light component corresponding to the distortion-corrected billet image, determining the perspective of each pixel point in the distortion-corrected billet image according to the atmospheric light component, and performing defogging treatment on the distortion-corrected billet image according to the atmospheric light component and the perspective;
And stretching the gray value of each pixel point in the defogging-treated billet image by a linear transformation method to obtain the billet image after the contrast enhancement treatment.
Optionally, the image processing module is configured to:
calculating the average gray value of each local window in the billet image after the contrast enhancement treatment, and respectively calculating the deviation between the gray value and the average gray value of each pixel to be identified in the billet image after the contrast enhancement treatment;
If the deviation is larger than the deviation threshold, determining the pixel point to be identified as a foreground pixel point, otherwise, determining the pixel point to be identified as a background pixel point;
determining a foreground region according to the foreground pixel points, and scanning the background pixel points in the foreground region;
Holes in the foreground region are determined based on the scan results and filled.
Optionally, the image processing module is configured to:
traversing pixel points in the foreground region, and determining at least one connected region based on the adjacent relation of each pixel point;
Determining one communication area as a target communication area according to the area and the rectangle degree of each communication area;
Fitting an edge curve of the target communication area by using a three-point interpolation method to obtain a contour point set corresponding to the target communication area.
Optionally, the angle detection module is configured to:
preprocessing the contour point set, and performing initial fitting on the preprocessed contour point set by using a least square fitting method to obtain a fitting rectangle;
calculating residual errors from each contour point in the preprocessed contour point set to the fitting rectangle respectively, and weighting the residual errors;
And fitting again according to the weighted residual errors to obtain new fitted rectangles, returning to the step of respectively calculating the residual errors from each contour point in the preprocessed contour point set to the fitted rectangle until the preset iteration termination condition is reached, and determining that the current fitted rectangle is the circumscribed minimum rectangle.
Optionally, the weight corresponding to the residual is inversely related to the residual.
Optionally, the apparatus further comprises a camera parameter acquisition module for:
And shooting a plurality of calibration plate pictures with different angles by using the target camera, and calibrating the target camera based on the calibration plate pictures to obtain camera parameters, wherein the camera parameters comprise internal parameters, external parameters and distortion parameters.
According to still another aspect of the present application, there is provided a medium having stored thereon a program or instructions which, when executed by a processor, implements the above-described medium plate steel angle reinforcing detection method.
It should be noted that, other corresponding descriptions of each functional module related to the device for detecting the steel-turning angle enhancement of the medium plate provided by the embodiment of the present application may refer to corresponding descriptions in the above method, and are not repeated here.
Based on the above method, correspondingly, the embodiment of the application also provides a storage medium, on which a computer program is stored, and the program is executed by a processor to realize the method for detecting the steel turning angle enhancement of the medium plate.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing an electronic device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
Based on the method shown in fig. 1 to 13 and the virtual device embodiment shown in fig. 14, in order to achieve the above object, an embodiment of the present application further provides an apparatus, which may specifically be a personal computer, a server, a network device, etc., where the electronic apparatus includes a storage medium and a processor; a storage medium storing a computer program; and the processor is used for executing a computer program to realize the method for detecting the steel rotation angle enhancement of the medium plate shown in the figures 1 to 13.
Optionally, the electronic device may also include a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, and the like. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., bluetooth interface, WI-FI interface), etc.
It will be appreciated by those skilled in the art that the structure of the electronic device provided in this embodiment is not limited to the electronic device, and may include more or fewer components, or may be combined with certain components, or may be arranged with different components.
The storage medium may also include an operating system, a network communication module. An operating system is a program that manages and saves electronic device hardware and software resources, supporting the execution of information handling programs, as well as other software and/or programs. The network communication module is used for realizing communication among all the controls in the storage medium and communication with other hardware and software in the entity equipment.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware.
Those skilled in the art will appreciate that the drawing is merely a schematic illustration of one preferred implementation scenario and that elements or processes in the drawing are not necessarily required to practice the application. Those skilled in the art will appreciate that elements of an apparatus in an implementation may be distributed throughout the apparatus in an implementation as described in the implementation, or that corresponding variations may be located in one or more apparatuses other than the present implementation. The units of the implementation scenario may be combined into one unit, or may be further split into a plurality of sub-units.
The above-mentioned inventive sequence numbers are merely for description and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely illustrative of some embodiments of the application, and the application is not limited thereto, as modifications may be made by those skilled in the art without departing from the scope of the application.
Claims (10)
1. The method for detecting the steel rotation angle enhancement of the medium plate is characterized by comprising the following steps of:
shooting a billet image through a target camera in a steel turning link of the medium plate rolling, and carrying out distortion correction on the billet image according to camera parameters of the target camera;
sequentially performing defogging treatment and contrast enhancement treatment on the distortion corrected billet image;
based on the gray scale of each pixel point in the billet image after the contrast enhancement treatment, a foreground area and a background area are identified, and holes in the foreground area are filled;
performing image morphology opening operation on the billet image filled with the holes;
determining a target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area;
Fitting an circumscribed minimum rectangle corresponding to the target communication area according to the edge profile, and determining a billet angle according to the offset angle of the rectangle relative to a preset reference direction.
2. The method according to claim 1, wherein the sequentially performing defogging processing and contrast enhancement processing on the distortion-corrected billet image comprises:
determining an atmospheric light component corresponding to the distortion-corrected billet image, determining the perspective of each pixel point in the distortion-corrected billet image according to the atmospheric light component, and performing defogging treatment on the distortion-corrected billet image according to the atmospheric light component and the perspective;
And stretching the gray value of each pixel point in the defogging-treated billet image by a linear transformation method to obtain the billet image after the contrast enhancement treatment.
3. The method of claim 1, wherein the identifying the foreground region and the background region based on the gray level of each pixel point in the contrast enhanced billet image and filling the holes in the foreground region comprises:
Calculating the average gray value of each local window in the billet image after the contrast enhancement treatment, and respectively calculating the deviation between the gray value of each pixel to be identified in the billet image after the contrast enhancement treatment and the average gray value;
If the deviation is larger than a deviation threshold, determining the pixel point to be identified as a foreground pixel point, otherwise, determining the pixel point to be identified as a background pixel point;
determining the foreground region according to the foreground pixel points, and scanning the background pixel points in the foreground region;
and determining holes in the foreground region based on the scanning result, and filling the holes.
4. The method according to claim 1, wherein determining a target connected region based on the connected relation of foreground regions in the billet image after the opening operation, and fitting the edge contour of the target connected region, comprises:
traversing the pixel points in the foreground region, and determining the at least one connected region based on the adjacency relation of each pixel point;
Determining one communication area as the target communication area according to the area and the rectangular degree of each communication area;
fitting an edge curve of the target communication area by using a three-point interpolation method to obtain a contour point set corresponding to the target communication area.
5. The method of claim 1, wherein said fitting the circumscribed minimum rectangle corresponding to the target connected region according to the edge profile comprises:
Preprocessing the contour point set, and performing initial fitting on the preprocessed contour point set by using a least square fitting method to obtain a fitting rectangle;
calculating residual errors from each contour point in the preprocessed contour point set to the fitting rectangle respectively, and weighting the residual errors;
and fitting again according to the weighted residual errors to obtain new fitted rectangles, returning to the step of respectively calculating the residual errors from each contour point in the preprocessed contour point set to the fitted rectangles until the preset iteration termination condition is reached, and determining the current fitted rectangle as the circumscribed minimum rectangle.
6. The method of claim 5, wherein the weight corresponding to the residual is inversely related to the residual.
7. The method of claim 1, comprising, prior to said distortion correcting said billet image based on camera parameters of said target camera:
And shooting a plurality of calibration plate pictures with different angles by using the target camera, and calibrating the target camera based on the calibration plate pictures to obtain camera parameters, wherein the camera parameters comprise internal parameters, external parameters and distortion parameters.
8. The utility model provides a medium plate changes steel angle reinforcing detection device which characterized in that, the device includes:
The image shooting module is used for shooting a steel billet image through a target camera in a steel turning link of the medium plate rolling, and carrying out distortion correction on the steel billet image according to camera parameters of the target camera;
The image processing module is used for sequentially carrying out defogging processing and contrast enhancement processing on the distortion corrected billet image; and identifying a foreground region and a background region based on the gray scale of each pixel point in the billet image after the contrast enhancement, and filling holes in the foreground region; and performing image morphology opening operation on the billet image after hole filling; determining a target communication area based on the communication relation of the foreground area in the billet image after the opening operation, and fitting the edge contour of the target communication area;
And the angle detection module is used for fitting the circumscribed minimum rectangle corresponding to the target communication area according to the edge profile and determining the angle of the billet according to the offset angle of the rectangle relative to the preset reference direction.
9. A storage medium having stored thereon a program or instructions which, when executed by a processor, implement the method of any of claims 1 to 7.
10. An electronic device comprising a storage medium and a processor, characterized in that the storage medium stores a computer program, which processor, when executing the computer program, implements the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410317919.7A CN117911419A (en) | 2024-03-20 | 2024-03-20 | Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410317919.7A CN117911419A (en) | 2024-03-20 | 2024-03-20 | Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117911419A true CN117911419A (en) | 2024-04-19 |
Family
ID=90684073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410317919.7A Pending CN117911419A (en) | 2024-03-20 | 2024-03-20 | Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117911419A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118710675A (en) * | 2024-08-27 | 2024-09-27 | 陕西首铝模架科技有限公司 | Extrusion integrated forming method and device for high-strength alloy template |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101574709A (en) * | 2009-06-12 | 2009-11-11 | 东北大学 | Automatic steel rotation method for medium plates |
| KR20100120791A (en) * | 2009-05-07 | 2010-11-17 | 엘지이노텍 주식회사 | Apparatus for measuring rotation angle and method for operating the same |
| CN104634261A (en) * | 2014-12-05 | 2015-05-20 | 浙江理工大学 | Line laser source based medium plate shape inspection system and method |
| CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
| CN109190628A (en) * | 2018-08-15 | 2019-01-11 | 东北大学 | A kind of plate camber detection method based on machine vision |
| WO2022127217A1 (en) * | 2020-12-18 | 2022-06-23 | 华能(福建漳州)能源有限责任公司 | Rotation angle measurement mechanism of stacker-reclaimer |
| CN116740332A (en) * | 2023-06-01 | 2023-09-12 | 南京航空航天大学 | Method for positioning center and measuring angle of space target component on satellite based on region detection |
| WO2023185118A1 (en) * | 2022-03-29 | 2023-10-05 | 广东利元亨智能装备股份有限公司 | Image processing method and apparatus, electronic device, and storage medium |
| WO2024007614A1 (en) * | 2022-07-08 | 2024-01-11 | 中交第二航务工程局有限公司 | Construction control method for partition type concrete diaphragm wall anchorage foundation |
-
2024
- 2024-03-20 CN CN202410317919.7A patent/CN117911419A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100120791A (en) * | 2009-05-07 | 2010-11-17 | 엘지이노텍 주식회사 | Apparatus for measuring rotation angle and method for operating the same |
| CN101574709A (en) * | 2009-06-12 | 2009-11-11 | 东北大学 | Automatic steel rotation method for medium plates |
| CN104634261A (en) * | 2014-12-05 | 2015-05-20 | 浙江理工大学 | Line laser source based medium plate shape inspection system and method |
| CN104981105A (en) * | 2015-07-09 | 2015-10-14 | 广东工业大学 | Detecting and error-correcting method capable of rapidly and accurately obtaining element center and deflection angle |
| CN109190628A (en) * | 2018-08-15 | 2019-01-11 | 东北大学 | A kind of plate camber detection method based on machine vision |
| WO2022127217A1 (en) * | 2020-12-18 | 2022-06-23 | 华能(福建漳州)能源有限责任公司 | Rotation angle measurement mechanism of stacker-reclaimer |
| WO2023185118A1 (en) * | 2022-03-29 | 2023-10-05 | 广东利元亨智能装备股份有限公司 | Image processing method and apparatus, electronic device, and storage medium |
| WO2024007614A1 (en) * | 2022-07-08 | 2024-01-11 | 中交第二航务工程局有限公司 | Construction control method for partition type concrete diaphragm wall anchorage foundation |
| CN116740332A (en) * | 2023-06-01 | 2023-09-12 | 南京航空航天大学 | Method for positioning center and measuring angle of space target component on satellite based on region detection |
Non-Patent Citations (3)
| Title |
|---|
| 张旭昶: "基于图像处理技术的矩形类零件测量方法的研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》, 15 April 2013 (2013-04-15), pages 62 - 64 * |
| 秦豆豆 等: "工件外观识别与视觉检测技术的研究", 《组合机床与自动化加工技术》, 30 September 2018 (2018-09-30), pages 84 - 88 * |
| 郝丁丁;王渊;郭卫;: "基于机器视觉的液压支架高度测量方法", 现代电子技术, no. 02, 15 January 2020 (2020-01-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118710675A (en) * | 2024-08-27 | 2024-09-27 | 陕西首铝模架科技有限公司 | Extrusion integrated forming method and device for high-strength alloy template |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866924B (en) | Line structured light center line extraction method and storage medium | |
| CN109816652B (en) | Complex casting defect identification method based on gray level significance | |
| CN115096206B (en) | High-precision part size measurement method based on machine vision | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN111161222B (en) | Printing roller defect detection method based on visual saliency | |
| CN111354047B (en) | Computer vision-based camera module positioning method and system | |
| CN117911419A (en) | Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment | |
| CN115170669A (en) | Identification and positioning method and system based on edge feature point set registration and storage medium | |
| JP5812705B2 (en) | Crack detection method | |
| CN116152261B (en) | Visual inspection system for quality of printed product | |
| CN110648330A (en) | Defect detection method for camera glass | |
| CN114332081B (en) | Textile surface abnormity determination method based on image processing | |
| CN114219802B (en) | Skin connecting hole position detection method based on image processing | |
| CN117635615B (en) | Defect detection method and system for realizing punching die based on deep learning | |
| CN109671084B (en) | Method for measuring shape of workpiece | |
| CN114998571A (en) | Image processing and color detection method based on fixed-size marker | |
| CN111476792B (en) | Extraction method of strip steel image contour | |
| CN116823827B (en) | Ore crushing effect evaluation method based on image processing | |
| CN114155226A (en) | Micro defect edge calculation method | |
| CN113223098A (en) | Preprocessing optimization method for image color classification | |
| CN113223074A (en) | Underwater laser stripe center extraction method | |
| CN112102189A (en) | Method for extracting central line of light strip of line structure | |
| CN113643290B (en) | Straw counting method and device based on image processing and storage medium | |
| CN110298799B (en) | PCB image positioning correction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |