Distance determination method and device, equipment and medium
By identifying parameters and defects on the end images of the steel coil, and calculating the number of layers and distances in combination with the thickness of the steel coil, the problem of difficult to determine the distance between the steel coil defects and the head and tail in the prior art is solved, and an accurate analysis of the change law of strip quality is achieved.
Patent Information
- Application Number
- CN202510120588.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-25
- Publication Date
- 2025-05-09
AI Technical Summary
The prior art is difficult to determine the distance between the steel coil defect and the head and tail of the steel coil, which affects the accuracy of the strip quality analysis, and thus cannot effectively trace the manifestation of the strip defect in the upstream and downstream processes.
Through the end image of the target steel coil, the target steel coil parameters and the end defect parameters of the steel coil are determined, combined with the thickness of the steel coil, the target number and target distance are calculated, including the distance between the defect position and the head and tail of the steel coil.
The accurate determination of the distance between the end defects of the steel coil from the head and tail of the steel coil can be traced, and the manifestation of the strip defects in the upstream and downstream processes can be analyzed and the strip quality changes are analyzed.
Smart Images
Figure CN119959222A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of steel coil end detection, and in particular to a distance determination method, device, equipment and medium. Background Art
[0002] As users' requirements for strip product quality increase, strips are required to have good edge quality. The main end defects at present are: burrs, edge cracks, pinching, scratches, etc. In addition, the defects at the ends of hot-rolled steel coils also have an important impact on the subsequent rolling process. For example, edge cracks can easily cause strip breakage when the strip enters the cold rolling process. When the burrs are serious, the defective coils need to be blocked, which in turn affects production efficiency.
[0003] Currently, intelligent equipment and intelligent recognition algorithms have been developed to realize image acquisition, automatic recognition and classification of defects at the end of steel coils. However, there is currently a lack of a method to determine the distance between the end defects of hot-rolled steel coils and the head and tail based on machine vision to trace the manifestation of strip defects in upstream and downstream processes, and then analyze the law of changes in strip quality. Summary of the invention
[0004] The present application provides a distance determination method, device, equipment and medium to solve the problem in the prior art that it is difficult to determine the distance between a steel coil defect and the head and tail of the steel coil, which in turn affects the quality analysis of the strip, thereby achieving accurate tracing of strip defects in upstream and downstream processes and accurate quality analysis of the strip.
[0005] In a first aspect, the present application provides a distance determination method, comprising:
[0006] Determine the target coil end image;
[0007] Based on the target coil end image, determining target coil parameters and coil end defect parameters;
[0008] Based on the target coil parameter, the coil end defect parameter and the coil thickness, a target number of layers is determined; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail;
[0009] Based on the target number of layers, the defect parameters of the steel coil end and the steel coil thickness, a target distance is determined; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
[0010] Optionally, the target steel coil parameters include a first radius of a circular area at the head of the steel coil, a second radius of a circular area at the tail of the steel coil, and the coordinates of the center of the steel coil; the steel coil end defect parameters include a third radius of a circular area of a defect at the end of the steel coil and the coordinates of the center of mass of the defect position at the end of the steel coil.
[0011] Optionally, determining target steel coil parameters and steel coil end defect parameters based on the target steel coil end image includes:
[0012] Fitting the contour information of the target steel coil end image to obtain the center coordinates of the steel coil; and determining the center coordinates by performing defect recognition on the target steel coil end image;
[0013] The first radius and the second radius are determined based on the center coordinates of the steel coil; and the third radius is determined based on the center coordinates of the steel coil, the center of mass coordinates and the unit pixel size of the target steel coil end image.
[0014] Optionally, determining the target number of layers based on the target steel coil parameter, the steel coil end defect parameter and the steel coil thickness includes:
[0015] Determining a thickness difference of the steel coil based on the first radius, the second radius, and the third radius;
[0016] The target number of layers is determined based on the steel coil thickness difference and the steel coil thickness.
[0017] Optionally, determining the target distance based on the target number of layers, the defect parameter of the steel coil end and the thickness of the steel coil includes:
[0018] Determining the circumference of one or more layers of the steel coil based on the target number of layers, the third radius and the thickness of the steel coil;
[0019] The circumference of each layer of steel coil is accumulated to obtain the target distance.
[0020] Optionally, determining the target coil end image includes:
[0021] During the movement of the target steel coil, multiple initial partial images of the end of the steel coil taken by multiple cameras at different positions at multiple times are obtained;
[0022] Determining a first coil end image based on the multiple initial partial images;
[0023] Threshold segmentation is performed on the first steel coil end image to obtain the target steel coil end image.
[0024] Optionally, determining the first coil end image based on the multiple initial partial images includes:
[0025] Based on the calibrated first overlapping area parameters taken by adjacent cameras and the calibrated second overlapping area parameters taken at adjacent moments, the plurality of initial partial images are cropped to obtain a plurality of cropped partial images;
[0026] The multiple cut partial images are spliced together according to preset rules to obtain the first steel coil end image.
[0027] In a second aspect, the present application further provides a distance determination device, comprising:
[0028] A first determination module is used to determine the target coil end image;
[0029] A second determination module is used to determine target steel coil parameters and steel coil end defect parameters based on the target steel coil end image;
[0030] A third determination module is used to determine a target number of layers based on the target coil parameter, the coil end defect parameter and the coil thickness; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail;
[0031] The fourth determination module is used to determine the target distance based on the target number of layers, the defect parameters of the steel coil end and the thickness of the steel coil; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
[0032] In a third aspect, the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.
[0033] In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.
[0034] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.
[0035] The distance determination method, device, equipment and medium provided in the present application determine the target steel coil parameters and the steel coil end defect parameters through the target steel coil end image, and then determine the target number of layers through the target steel coil parameters, the steel coil end defect parameters and the steel coil thickness, and then determine the target distance through the target number of layers, the coil end defect parameters and the steel coil thickness, so as to accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in the upstream and downstream processes, and analyze the law of strip quality changes. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0037] Figure 1 is a flow chart of a distance determination method provided in an embodiment of the present application;
[0038] Figure 2 This is one of the first steel coil end image schematic diagrams provided in the embodiment of the present application;
[0039] Figure 3 This is the second schematic diagram of the image of the end of the first steel coil provided in the embodiment of the present application;
[0040] Figure 4 is a schematic diagram of an image of a target steel coil end provided in an embodiment of the present application;
[0041] Figure 5 This is a schematic diagram of the structure of the distance determination device provided in the embodiment of the present application.
[0042] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0044] Figure 1 is a flow chart of the distance determination method provided in the embodiment of the present application. Figure 1The present application embodiment provides a distance determination method, the execution subject of which may be an electronic device, for example, a controller. The following description is made by taking the execution subject of the method as an example. The method may include:
[0045] Step 110, determining the target coil end image;
[0046] Step 120: determining target coil parameters and coil end defect parameters based on the target coil end image;
[0047] Step 130: determining a target number of layers based on target coil parameters, coil end defect parameters and coil thickness; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail;
[0048] Step 140, determining a target distance based on the target number of layers, the defect parameters at the end of the steel coil and the thickness of the steel coil; the target distance includes a first distance between the defect position at the end of the steel coil and the head of the steel coil and a second distance between the defect position at the end of the steel coil and the tail of the steel coil.
[0049] In step 110, the controller may acquire an initial partial image of the end of the steel coil by using cameras arranged according to a preset rule, and obtain a target steel coil end image by cropping and splicing the initial partial image.
[0050] In step 120, the controller may determine target coil parameters and coil end defect parameters based on the target coil end image. Specifically, the target coil parameters are parameters related to the coil, and the coil end defect parameters are parameters related to the coil end defect.
[0051] In step 130, the controller can determine the thickness of the steel coil defect position from the head and tail of the steel coil based on the target steel coil parameters and the steel coil end defect parameters, and then determine the target number of layers in combination with the steel coil thickness. Specifically, the target number of layers includes the first number of layers from the steel coil end defect position to the steel coil head and the second number of layers from the steel coil end defect position to the steel coil tail.
[0052] In step 140, the controller can calculate and accumulate the perimeter of each layer of the steel coil from the steel coil defect position to the head and tail of the steel coil based on the target number of layers, the steel coil end defect parameter and the steel coil thickness, so as to obtain the target distance. Specifically, the target distance includes a first distance between the steel coil end defect position and the steel coil head and a second distance between the steel coil end defect position and the steel coil tail.
[0053] The distance determination method provided in the embodiment of the present application determines the target steel coil parameters and the steel coil end defect parameters through the target steel coil end image, and then determines the target number of layers through the target steel coil parameters, the steel coil end defect parameters and the steel coil thickness, and then determines the target distance through the target number of layers, the coil end defect parameters and the steel coil thickness, so as to accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in the upstream and downstream processes, and analyze the law of strip quality changes.
[0054] In one embodiment, the target steel coil parameters include the first radius of the circular area at the head of the steel coil, the second radius of the circular area at the tail of the steel coil, and the coordinates of the center of the steel coil; the steel coil end defect parameters include the third radius of the circular area of the defect at the end of the steel coil and the coordinates of the center of mass of the defect position at the end of the steel coil.
[0055] Specifically, the circular area at the head of the steel coil is the inner circle of the steel coil, the circular area at the tail of the steel coil is the outer circle of the steel coil, and the circular area with defects at the end of the steel coil is the circle layer of the steel coil where the defects at the end of the steel coil are located.
[0056] The distance determination method provided in the embodiment of the present application determines the target number of layers by determining the target steel coil parameters and the steel coil end defect parameters, and then determines the target distance through the target number of layers, the coil end defect parameters and the steel coil thickness, so as to accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in the upstream and downstream processes, and analyze the change law of strip quality.
[0057] In one embodiment, based on the target steel coil end image, target steel coil parameters and steel coil end defect parameters are determined, including: fitting the contour information of the target steel coil end image to obtain the coordinates of the center of the steel coil; and determining the center of mass coordinates by performing defect recognition on the target steel coil end image; determining the first radius and the second radius based on the steel coil center coordinates; and determining the third radius based on the steel coil center coordinates, the center of mass coordinates and the unit pixel size of the target steel coil end image.
[0058] The controller can fit the contour information of the target coil end image to obtain the center coordinates of the coil, and identify defects in the target coil end image to determine the center coordinates. For example, the controller can identify defects through machine vision technology or deep learning networks.
[0059] The controller can determine the pixel value of the first radius through the center coordinates of the steel coil, and then calculate the first radius in combination with the unit pixel size; determine the pixel value of the second radius through the center coordinates of the steel coil, and then calculate the second radius in combination with the unit pixel size. The specific calculation formula is as follows:
[0060] R In =R p In ×μ
[0061] R Ex =R p Ex ×μ
[0062] Among them, R In is the first radius, R p In is the pixel value of the first radius, μ is the unit pixel size, R Ex is the second radius, R p Ex is the pixel value of the second radius.
[0063] The controller can determine the third radius based on the center coordinates of the steel coil, the center of mass coordinates and the unit pixel size of the target steel coil end image, wherein the unit pixel size is obtained by calibration calculation and is calculated by dividing the horizontal field of view by the number of horizontal pixels of the image.
[0064] The specific calculation formula for the third radius is as follows:
[0065]
[0066] Among them, R T is the third radius, P C.X is the horizontal coordinate of the center of the steel coil, P T.X is the horizontal coordinate of the center of mass, P C.Y is the ordinate of the center of the coil, P T.Y is the centroid ordinate, and μ is the unit pixel size.
[0067] The distance determination method provided in the embodiment of the present application determines the target steel coil parameters and the steel coil end defect parameters through the target steel coil end image, and then determines the target distance, so as to accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in the upstream and downstream processes, and analyze the change law of strip quality.
[0068] In one embodiment, the target number of layers is determined based on the target coil parameters, the coil end defect parameters and the coil thickness, including: determining the coil thickness difference based on the first radius, the second radius and the third radius; determining the target number of layers based on the coil thickness difference and the coil thickness.
[0069] Specifically, the thickness difference of the steel coil includes a first thickness difference between the defect position at the end of the steel coil and a circular area at the head of the steel coil, and a second thickness difference between the defect position at the end of the steel coil and a circular area at the tail of the steel coil.
[0070] The calculation formula for determining the target number of layers is as follows:
[0071]
[0072] Among them, N In is the first layer number, R T is the third radius, R In is the first radius, (R T -R In ) is the first thickness difference, T is the thickness of the steel coil, N Ex is the second layer number, R Ex is the second radius, (R Ex -R T ) is the second thickness difference.
[0073] It is worth noting that in this application, the total target number of steel coil layers can also be calculated to verify the accuracy of the target number of layers. The calculation formula for the total target number of steel coil layers is as follows:
[0074]
[0075] Where N is the total number of target coil layers, R Ex is the second radius, R In is the first radius and T is the thickness of the steel coil.
[0076] In addition, the calculation process of the above-mentioned target number of layers and the total target number of steel coil layers retains integers.
[0077] The distance determination method provided in the embodiment of the present application determines the target number of layers and then the target distance through the target steel coil parameters, the steel coil end defect parameters and the steel coil thickness, so as to accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in the upstream and downstream processes and analyze the change law of strip quality.
[0078] In one embodiment, the target distance is determined based on the target number of layers, the defect parameters of the steel coil end and the thickness of the steel coil, including: determining the circumference of one or more layers of the steel coil based on the target number of layers, the third radius and the thickness of the steel coil; and accumulating the circumference of each layer of the steel coil to obtain the target distance.
[0079] The specific calculation formula for the target distance is as follows:
[0080]
[0081] Among them, L In is the first distance, N In is the first layer number, R T is the third radius, T is the thickness of the steel coil, L Ex is the second distance, N Ex It is the second layer.
[0082] The distance determination method provided in the embodiment of the present application determines the target distance through the target number of layers, the defect parameters of the steel coil end and the steel coil thickness, and can accurately determine the distance between the defect at the end of the steel coil and the head and tail of the steel coil, and then trace the manifestation of strip defects in the upstream and downstream processes, and analyze the change law of strip quality.
[0083] In one embodiment, determining a target steel coil end image includes: acquiring multiple initial local images of the steel coil end taken by multiple cameras at different positions at multiple moments during the movement of the target steel coil; determining a first steel coil end image based on the multiple initial local images; and performing threshold segmentation on the first steel coil end image to obtain a target steel coil end image.
[0084] The controller can arrange multiple cameras in a direction perpendicular to the moving direction of the target steel coil. After cropping and splicing multiple initial partial images of the steel coil end taken by the multiple cameras at multiple times, a complete steel coil end image, i.e., the first steel coil end image, can be obtained. Figure 2 This is one of the first steel coil end image schematic diagrams provided in the embodiments of the present application. Figure 3 This is the second of the first steel coil end image schematic diagrams provided in the embodiment of the present application.
[0085] The controller can obtain the target steel coil end image by performing threshold segmentation on the first steel coil end image. Figure 4 : is a schematic diagram of the target steel coil end image provided in the embodiment of the present application. Among them, the target steel coil end surface is in a highlighted state and is segmented into white pixels by threshold value, and other areas are in a dark state and are segmented into black pixels by threshold value.
[0086] The distance determination method provided in the embodiment of the present application can accurately determine the distance between the defect at the end of the steel coil and the head and tail of the steel coil by determining the image of the end of the target steel coil and determining the target distance, and then trace the manifestation of the strip defects in the upstream and downstream processes and analyze the change law of the strip quality.
[0087] In one embodiment, based on multiple initial partial images, a first steel coil end image is determined, including: based on calibrated first overlapping area parameters taken by adjacent cameras and second overlapping area parameters taken at adjacent moments, the multiple initial partial images are cropped to obtain multiple cropped partial images; and the multiple cropped partial images are spliced according to preset rules to obtain the first steel coil end image.
[0088] The controller can use m cameras distributed at equal intervals along the longitudinal direction to collect initial local images, collect images of different positions of the end of the steel coil n times (i.e., n moments) during the movement of the steel coil, and obtain a total of m×n different initial local images of the steel coil. Then, according to the calibrated first and second overlapping area parameters of adjacent cameras and adjacent moments in the same coordinate system, the initial local image is cropped.
[0089] Specifically, m cameras are arranged vertically from top to bottom, with the same size of horizontal field of view, and there are overlapping areas in the vertical field of view between adjacent cameras; there is an overlapping area in the bottom area of the field of view of the upper camera and the top area of the field of view of the lower camera. During the movement of the target steel coil, the cameras at each position collect n images, and the size of the vertical field of view of the adjacent images collected by the same camera is exactly the same, and there are overlapping areas in the horizontal field of view of the adjacent images collected by the same camera; there is an overlapping area on the right side of the field of view of the image at the previous collection time and on the left side of the field of view of the image at the next collection time.
[0090] Preferably, the present application may use three cameras that are evenly spaced longitudinally, and the cameras may be high-resolution industrial cameras. During the movement of the steel coil, images of different positions of the end of the target steel coil are collected three times, and a total of nine initial partial images are obtained. Specifically, in the present application, there is an upper middle camera field of view overlapping area H1 and a middle lower camera field of view overlapping area H2, and H1 and H2 are the first overlapping area parameters. The first and second (adjacent moments) acquisition position field of view overlapping area W1, the second and third (adjacent moments) acquisition position field of view overlapping area W2, and W1 and W2 are the second overlapping area parameters.
[0091] If the size of the collected single initial partial image is W pixels × H pixels, then the size of the complete image stitched together by the nine images should be (W × 3-W1-W2) pixels × (H × 3-H1-H2) pixels. The origin of the image pixel coordinate system is in the upper left corner, with the horizontal rightward axis as the positive axis of the horizontal coordinate axis and the vertical downward axis as the positive axis of the vertical coordinate axis.
[0092] The specific cutting rules are:
[0093] The upper camera captures the image for the first time, with the cropping starting point at (0, 0) and the cropping size at (W-W1)×(H-H1). The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (0, 0) of the complete image.
[0094] The middle camera collects the image for the first time, with the cropping starting point at (0, 0) and the cropping size at (W-W1)×H. The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (0, H-H1) of the complete image.
[0095] The lower camera collects the image for the first time, the cropping starting point is (0, H2), the cropping size is (W-W1)×(H-H2), and the cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (0, 2×H-H1) of the complete image;
[0096] The upper camera collects the image for the second time, with the cropping starting point at (0, 0) and the cropping size at W×(H-H1). The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (W-W1, 0) of the complete image.
[0097] The middle camera collects the image for the second time, with the cropping starting point at (0, 0) and the cropping size at W×H. The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (W-W1, H-H1) of the complete image.
[0098] The lower camera collects the image for the second time, with the cropping starting point at (0, H2) and the cropping size at W×(H-H2). The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (W-W1, 2×H-H1) of the complete image.
[0099] The upper camera collects the image for the third time, with the cropping starting point at (W2, 0) and the cropping size at (W-W2)×(H-H1). The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (2×W-W1, 0) of the complete image.
[0100] The middle camera collects the image for the third time, with the cropping starting point at (W2, 0) and the cropping size at (W-W2)×H. The cropped partial image is obtained, and its upper left corner anchor point is placed at the coordinate point (2×W-W1, H-H1) of the complete image.
[0101] The lower camera captures the image for the third time. The cropping starting point is (W2, H2) and the cropping size is (W-W2)×(H-H2). The cropped partial image is obtained and its upper left corner anchor point is placed at the coordinate point (2×W-W1, 2×H-H1) of the complete image.
[0102] The controller splices the 9 cropped partial images placed at the upper left corner anchor point to obtain the first steel coil end image.
[0103] The distance determination method provided in the embodiment of the present application determines the first steel coil end image through multiple initial local images, and then determines the target distance, which can improve the clarity of the steel coil end image, and then accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in upstream and downstream processes, and analyze the quality change law of the strip.
[0104] Based on the description of the above embodiments, the present application also provides an application example of using the method of the present application to calculate the distance, and the specific steps are as follows:
[0105] S1, obtaining a complete steel coil end image, that is, a first steel coil end image;
[0106] S1-1. Select three industrial cameras with equal spacing in the longitudinal direction, collect images of different positions of the end of the steel coil three times during the movement of the steel coil, and obtain a total of 9 different initial local images of the end of the steel coil;
[0107] Each camera collects a single-channel 8-bit depth image with a resolution of 5120×5120. The field of view of a single camera is 768mm×768mm, so the unit pixel size is 0.15mm / pixel.
[0108] S1-2, according to the calibrated overlapping area parameters between adjacent cameras and adjacent acquisition times, cropping the corresponding areas of the images at different positions, and placing the multiple cropped partial images after the overlapping areas are cropped at corresponding positions;
[0109] In this example, the size of the upper middle camera field of view overlap area H1 is 260 pixels, and the size of the middle and lower camera field of view overlap area H2 is 200 pixels. The size of the first and second acquisition position field of view overlap area W1 is 80 pixels, and the size of the second and third acquisition position field of view overlap area W2 is 1100 pixels.
[0110] In this example, the size of a single image is 5120 pixels × 5120 pixels, and the size of the complete image stitched together by nine images should be 14180 pixels × 14900 pixels. The origin of the image pixel coordinate system is in the upper left corner, with the horizontal axis pointing to the right as the positive axis of the horizontal coordinate axis, and the vertical axis pointing downward as the positive axis of the vertical coordinate axis;
[0111] The upper camera captures the image for the first time, the cropping start point is (0, 0), the cropping size is 5040×4860, and the upper left corner anchor point is placed at the coordinate point (0, 0) of the complete image;
[0112] The middle camera collects the image for the first time, the cropping starting point is (0, 0), the cropping size is 5040×5120, and the upper left corner anchor point is placed at the coordinate point (0, 4860) of the complete image;
[0113] The camera below collects the image for the first time, the cropping start point is (0, 200), the cropping size is 5040×4920, and the upper left corner anchor point is placed at the coordinate point (0, 9980) of the complete image;
[0114] The upper camera collects the image for the second time, the cropping starting point is (0, 0), the cropping size is 5120×4860, and the upper left corner anchor point is placed at the coordinate point (5040, 0) of the complete image;
[0115] The middle camera collects the image for the second time, with the cropping starting point at (0, 0), the cropping size at 5120×5120, and the upper left corner anchor point at the coordinate point (5040, 4860) of the complete image;
[0116] The lower camera collects the image for the second time, with the cropping starting point at (0, 200), the cropping size at 5120×4920, and the upper left corner anchor point at the coordinate point (5040, 9980) of the complete image;
[0117] The upper camera collects the image for the third time, the cropping starting point is (1100, 0), the cropping size is 4020×4860, and the upper left corner anchor point is placed at the coordinate point (10160, 0) of the complete image;
[0118] The middle camera collects images for the third time, with the cropping starting point at (1100, 0), the cropping size at 4020×5120, and the upper left corner anchor point at the coordinate point (10160, 4860) of the complete image;
[0119] The lower camera collects the image for the third time, the cropping starting point is (1100, 200), the cropping size is 4020×4920, and the upper left corner anchor point is placed at the coordinate point (10160, 9980) of the complete image;
[0120] S1-3, obtaining an image of the end of the first steel coil;
[0121] The 9 cropped partial images with the upper left corner anchor point placed are spliced to obtain the first steel coil end image, and the first steel coil end image is threshold segmented to obtain the target steel coil end image.
[0122] Case 1: The defect at the end of the steel coil is a broken edge defect;
[0123] S2-1, obtain the steel coil thickness as 3 mm and the unit pixel size as 0.15 mm / pixel;
[0124] S2-2, fitting the center position of the steel coil according to the contour information, and calculating the first radius of the circular area at the head of the steel coil and the second radius of the circular area at the tail of the steel coil;
[0125] The calculation shows that the center coordinates of the steel coil are (6760, 9118), the first radius is 372.286 mm, the second radius is 868.21 mm, and the total number of target steel coil layers is 165;
[0126] S3-1, obtaining the third radius of the circular defect area at the end of the steel coil and the centroid coordinates of the defect position at the end of the steel coil;
[0127] The calculation shows that the coordinates of the center of mass are (8,038, 13,688) and the third radius is 711.714 mm;
[0128] S3-2, calculate the first layer number of the defect position at the end of the steel coil from the head of the steel coil and the second layer number of the defect position at the end of the steel coil from the tail of the steel coil;
[0129] The calculation shows that the first number of layers is 113 and the second number of layers is 52;
[0130] S3-3, calculating a first distance between the defect position at the end of the steel coil and the head of the steel coil and a second distance between the defect position at the end of the steel coil and the tail of the steel coil;
[0131] Calculation shows that the first distance is 388.137m and the second distance is 262.982m.
[0132] Case 2: The end defect of the steel coil is an edge damage defect
[0133] S2-1, obtain the steel coil thickness as 4 mm and the unit pixel size as 0.15 mm / pixel;
[0134] S2-2, fitting the center position of the steel coil according to the contour information, and calculating the first radius and the second radius;
[0135] The calculation shows that the center coordinates of the steel coil are (6642, 9086), the first radius is 372.581 mm, the second radius is 873.13 mm, and the number of steel coil layers is 125;
[0136] S3-1, obtaining the third radius and the center of mass coordinates;
[0137] Calculation shows that the coordinates of the center of mass are (6048, 6586) and the third radius is 385.501 mm;
[0138] S3-2, calculate the target number of layers;
[0139] The calculation shows that the first number of layers is 3, and the second number of layers is 122;
[0140] S3-3, calculating the target distance;
[0141] Calculation shows that the first distance is 9.514m and the second distance is 481.01m.
[0142] The distance determination device provided in the present application is described below. The distance determination device described below and the distance determination method described above can refer to each other.
[0143] Figure 5 is a schematic diagram of the structure of the distance determination device provided in the embodiment of the present application. Figure 3 The distance determination device provided in the embodiment of the present application may include:
[0144] A first determination module 510 is used to determine the target coil end image;
[0145] A second determination module 520 is used to determine target coil parameters and coil end defect parameters based on the target coil end image;
[0146] The third determination module 530 is used to determine the target number of layers based on the target coil parameter, the coil end defect parameter and the coil thickness; the target number of layers includes the first number of layers from the coil end defect position to the coil head and the second number of layers from the coil end defect position to the coil tail;
[0147] The fourth determination module 540 is used to determine the target distance based on the target number of layers, the defect parameters of the steel coil end and the thickness of the steel coil; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
[0148] The distance determination device provided in the embodiment of the present application determines the target steel coil parameters and the steel coil end defect parameters through the target steel coil end image, and then determines the target number of layers through the target steel coil parameters, the steel coil end defect parameters and the steel coil thickness, and then determines the target distance through the target number of layers, the coil end defect parameters and the steel coil thickness, so as to accurately determine the distance between the steel coil end defect and the steel coil head and tail, and then trace the manifestation of strip defects in the upstream and downstream processes, and analyze the law of strip quality changes.
[0149] Specifically, the above-mentioned distance determination device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the execution subject is the controller, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.
[0150] Figure 6 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the distance determination method, for example, including:
[0151] Determine the target coil end image;
[0152] Based on the target coil end image, determining target coil parameters and coil end defect parameters;
[0153] Based on the target coil parameter, the coil end defect parameter and the coil thickness, a target number of layers is determined; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail;
[0154] Based on the target number of layers, the defect parameters of the steel coil end and the steel coil thickness, a target distance is determined; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
[0155] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-On l yMemory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.
[0156] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the steps of the distance determination method provided by the above methods, for example, including:
[0157] Determine the target coil end image;
[0158] Based on the target coil end image, determining target coil parameters and coil end defect parameters;
[0159] Based on the target coil parameter, the coil end defect parameter and the coil thickness, a target number of layers is determined; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail;
[0160] Based on the target number of layers, the defect parameters of the steel coil end and the steel coil thickness, a target distance is determined; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
[0161] In another aspect, the present application further provides a computer program product, the computer program product comprising a computer program, the computer program may be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the steps of the distance determination method provided by the above methods, for example, including:
[0162] Determine the target coil end image;
[0163] Based on the target coil end image, determining target coil parameters and coil end defect parameters;
[0164] Based on the target coil parameter, the coil end defect parameter and the coil thickness, a target number of layers is determined; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail;
[0165] Based on the target number of layers, the defect parameters of the steel coil end and the steel coil thickness, a target distance is determined; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
[0166] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0167] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0168] It should also be noted that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.
[0169] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.
[0170] "Determine B based on A" in the embodiments of the present application means that the factor A should be considered when determining B. It is not limited to "B can be determined based on A alone", but should also include: "Determine B based on A and C", "Determine B based on A, C and E", "Determine C based on A, and further determine B based on C", etc. In addition, it can also include taking A as a condition for determining B, for example, "When A meets the first condition, use the first method to determine B"; for another example, "When A meets the second condition, determine B", etc.; for another example, "When A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor for determining B, for example, "When A meets the first condition, use the first method to determine C, and further determine B based on C", etc.
[0171] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.
[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A distance determination method, characterized in that: include: Determine the target coil end image; Based on the target coil end image, determining target coil parameters and coil end defect parameters; Based on the target coil parameter, the coil end defect parameter and the coil thickness, a target number of layers is determined; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail; Based on the target number of layers, the defect parameters of the steel coil end and the steel coil thickness, a target distance is determined; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
2. The distance determination method according to claim 1, characterized in that: The target coil parameters include the first radius of the coil head circular area, the second radius of the coil tail circular area and the center coordinates of the coil; the coil end defect parameters include the third radius of the coil end defect circular area and the center coordinates of the coil end defect position.
3. The distance determination method according to claim 2, characterized in that: The determining of target steel coil parameters and steel coil end defect parameters based on the target steel coil end image includes: Fitting the contour information of the target steel coil end image to obtain the center coordinates of the steel coil; and determining the center coordinates by performing defect recognition on the target steel coil end image; The first radius and the second radius are determined based on the center coordinates of the steel coil; and the third radius is determined based on the center coordinates of the steel coil, the center of mass coordinates and the unit pixel size of the target steel coil end image.
4. The distance determination method according to claim 2, characterized in that: The step of determining a target number of layers based on the target coil parameter, the coil end defect parameter and the coil thickness includes: Determining a thickness difference of the steel coil based on the first radius, the second radius, and the third radius; The target number of layers is determined based on the steel coil thickness difference and the steel coil thickness.
5. The distance determination method according to claim 2, characterized in that: The determining of the target distance based on the target number of layers, the defect parameter of the steel coil end and the thickness of the steel coil includes: Determining the circumference of one or more layers of the steel coil based on the target number of layers, the third radius and the thickness of the steel coil; The circumference of each layer of steel coil is accumulated to obtain the target distance.
6. The distance determination method according to claim 1, characterized in that: The step of determining the target coil end image comprises: During the movement of the target steel coil, multiple initial partial images of the end of the steel coil taken by multiple cameras at different positions at multiple times are obtained; Determining a first coil end image based on the multiple initial partial images; Threshold segmentation is performed on the first steel coil end image to obtain the target steel coil end image.
7. The distance determination method according to claim 6, characterized in that: The step of determining the first coil end image based on the plurality of initial partial images comprises: Based on the calibrated first overlapping area parameters taken by adjacent cameras and the calibrated second overlapping area parameters taken at adjacent moments, the plurality of initial partial images are cropped to obtain a plurality of cropped partial images; The multiple cut partial images are spliced together according to preset rules to obtain the first steel coil end image.
8. A distance determination device, characterized in that: include: A first determination module is used to determine the target coil end image; A second determination module is used to determine target steel coil parameters and steel coil end defect parameters based on the target steel coil end image; A third determination module is used to determine a target number of layers based on the target coil parameter, the coil end defect parameter and the coil thickness; the target number of layers includes a first number of layers from the coil end defect position to the coil head and a second number of layers from the coil end defect position to the coil tail; The fourth determination module is used to determine the target distance based on the target number of layers, the defect parameters of the steel coil end and the thickness of the steel coil; the target distance includes a first distance between the defect position of the steel coil end and the head of the steel coil and a second distance between the defect position of the steel coil end and the tail of the steel coil.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the distance determination method according to any one of claims 1 to 7 is implemented.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the distance determination method according to any one of claims 1 to 6 is implemented.