Cooling bed wide and thick plate positioning method and device, electronic equipment and storage medium

Abstract

The invention provides a cooling bed wide and thick plate positioning method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the mask segmentation of a wide and thick plate image based on the collection of the wide and thick plate image, obtaining a plurality of segmented mask images, splicing the plurality of segmented mask images, and obtaining a spliced mask image, extracting a center line and a center point coordinate of the wide and thick plate in the spliced mask image as an image center line and an image center point, converting the image center line and the image center point coordinate to a preset coordinate system to obtain an actual center line and an actual center point coordinate, and obtaining a target area according to a preset direction vector and the actual center point coordinate of a roller way in the target area; calculating the reference distance between the wide and thick plate and the roller way, calculating the included angle between the wide and thick plate and the edge line of the roller way according to the actual center line, obtaining the positioning result of the wide and thick plate in the target area according to the included angle and the reference distance, and triggering an alarm when the positioning result is abnormal.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, specifically to a method, apparatus, electronic device, and storage medium for positioning a wide and thick plate on a cooling bed. Background Technology

[0002] Heavy plates are a key structural material widely used in large bridges, nuclear power plants, dams, ships, heavy machinery, and weaponry. With the increasing demands on material performance from various major projects, heavy plates face higher standards in terms of strength, thickness, and overall quality. my country has built several mature heavy plate production lines, with capacity increasing year by year and production pace accelerating. This poses a severe challenge to the stability and control precision of the process flow. In the cooling stage after heavy plate rolling, the cooling bed, as a key piece of equipment, plays a crucial role in the step-by-step cooling and finishing of the steel plate. To ensure the smooth movement of the steel plate on the cooling bed and avoid stacking or shifting, precise judgment of its position when entering and leaving the cooling bed is essential.

[0003] Currently, traditional production methods generally employ manual monitoring, requiring operators to visually inspect the placement and alignment of each steel plate at the entrance and exit of the cooling bed. This method only allows for qualitative judgment, heavily relies on the operator's experience and focus, and suffers from strong subjectivity and poor consistency, easily leading to misjudgments due to fatigue or negligence. Furthermore, the cooling bed area is a harsh environment, typically accompanied by intense noise and high-temperature radiation, which not only affects the health and safety of personnel but also limits the feasibility of long-term continuous operation. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for positioning a thick plate on a cooling bed, in order to solve the technical problem that manual monitoring of the condition of a thick plate is prone to misjudgment.

[0005] This invention provides a method for locating a thick plate on a cooling bed. The method includes: acquiring an image of a thick plate in a target area of ​​the cooling bed, the image being acquired using an array camera; performing mask segmentation on the thick plate image to obtain multiple segmented mask images; stitching the multiple segmented mask images together to obtain a stitched mask image; extracting the centerline and center point coordinates of the thick plate in the stitched mask image as the image centerline and image center point; transforming the image centerline and image center point coordinates to a preset coordinate system according to the camera parameters of the array camera to obtain the actual centerline and actual center point coordinates, respectively; calculating a reference distance between the thick plate and the roller conveyor in the target area based on a preset direction vector of the roller conveyor and the actual center point coordinates; calculating the angle between the thick plate and the edge line of the roller conveyor based on the actual centerline; obtaining the positioning result of the thick plate in the target area based on the angle and the reference distance; and triggering an alarm when the positioning result is abnormal.

[0006] In one embodiment of the present invention, before acquiring the image of the thick plate in the target area of ​​the cooling bed, the method further includes: acquiring a roller conveyor image of the target area; identifying the thick plate in the roller conveyor image to obtain a detection frame of the thick plate; comparing the detection frame with a preset area to obtain the positioning state of the thick plate, wherein the preset area is the area in the roller conveyor image determined according to preset vertex coordinates; if the positioning state is in place, then acquiring an image of the thick plate based on the array camera.

[0007] In one embodiment of the present invention, comparing the detection frame with a preset area to obtain the positioning state of the thick plate includes: obtaining a set of rectangular frames based on the center coordinates, width, and position of the detection frame; obtaining a set of positioning areas based on the vertex coordinates of the preset area, and calculating the cross-over overlap rate between the set of rectangular frames and the set of positioning areas; if the cross-over overlap rate is greater than or equal to a preset overlap rate threshold, the positioning state is in place; if the cross-over overlap rate is less than the preset overlap rate threshold, the positioning state is not in place.

[0008] In one embodiment of the present invention, the image of the wide and thick plate is segmented by masking to obtain multiple segmentation mask images. The multiple segmentation mask images are then stitched together to obtain a stitched mask image. This process includes: scaling, translating, and rotating the multiple segmentation mask images based on preset scaling factors, preset translation parameters, and preset rotation parameters to obtain multiple processed segmentation mask images; stitching the multiple processed segmentation mask images based on corresponding preset stitching weights; and performing a convolution operation on the stitched image to obtain the stitched mask image.

[0009] In one embodiment of the present invention, transforming the image center line and the image center point coordinates to a preset coordinate system according to the camera parameters of the array camera includes: obtaining the aperture center coordinates of the camera aperture center point of the array camera in the preset coordinate system, and a first distance from the edge line of the thick plate to the array camera, wherein the camera parameters include at least the focal length; converting the image center point coordinates to actual center point coordinates in the preset coordinate system based on the first distance, the focal length, and the aperture center coordinates; converting the coordinates of any two points in the image center line to actual coordinates of two points in the preset coordinate system based on the first distance, the focal length, and the aperture center coordinates; and determining the actual center line based on the actual coordinates of the two points.

[0010] In one embodiment of the present invention, calculating the angle between the thick plate and the edge line of the roller conveyor based on the actual center line includes: calculating the angle between the thick plate and the edge line of the roller conveyor based on the inverse cosine function and the actual coordinates of the two points.

[0011] In one embodiment of the present invention, the positioning result of the thick plate in the target area is obtained according to the included angle and the reference distance, and the alarm is triggered when the positioning result is abnormal, including: if the included angle is greater than a preset included angle threshold, the positioning result has an included angle abnormality and an included angle abnormality alarm is triggered; if the reference distance is not within the preset distance range, the positioning result has a reference distance abnormality and a reference distance abnormality alarm is triggered.

[0012] This invention also provides a positioning device for a thick plate on a cooling bed. The device includes: an image stitching module for acquiring an image of a thick plate in a target area of ​​the cooling bed, the image being acquired using an array camera; performing mask segmentation on the image to obtain multiple segmented mask images; and stitching the multiple segmented mask images together to obtain a stitched mask image; a coordinate transformation module for extracting the centerline and center point coordinates of the thick plate in the stitched mask image as the image centerline and image center point, and transforming the image centerline and image center point coordinates to a preset coordinate system according to the camera parameters of the array camera to obtain the actual centerline and actual center point coordinates, respectively; a position calculation module for calculating a reference distance between the thick plate and the roller conveyor in the target area based on a preset direction vector of the roller conveyor and the actual center point coordinates, and calculating the angle between the thick plate and the edge line of the roller conveyor based on the actual centerline; and a positioning alarm module for obtaining the positioning result of the thick plate in the target area based on the angle and the reference distance, and triggering an alarm when the positioning result is abnormal.

[0013] The present invention also provides an electronic device, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device enables the cold bed thick plate positioning method as described in any of the above embodiments.

[0014] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a computer processor, causes the computer to perform any of the above embodiments of the cold bed thick plate positioning method.

[0015] The beneficial effects of this invention are as follows: This invention proposes a method, device, electronic device, and storage medium for positioning a thick plate on a cooling bed. Based on an acquired image of the thick plate, multiple segmented mask images are obtained by masking the image. These multiple segmented mask images are then stitched together to obtain a stitched mask image. The centerline and center point coordinates of the thick plate in the stitched mask image are extracted as the image centerline and image center point. The coordinates of the image centerline and image center point are then transformed to a preset coordinate system to obtain the actual centerline and actual center point coordinates. Based on the preset direction vector of the roller conveyor in the target area and the actual center point coordinates, the reference distance between the thick plate and the roller conveyor is calculated. This invention calculates the angle between the thick plate and the edge of the roller conveyor based on the actual centerline, and obtains the positioning result of the thick plate within the target area based on the angle and the reference distance. An alarm is triggered when there is an abnormality in the positioning result. This invention applies image recognition technology and deep learning technology to the cooling bed of the steel rolling production line to accurately position each thick plate, assisting personnel to quickly and accurately detect and correct positional anomalies in a timely manner. It solves the problem of not being able to quantitatively and accurately determine the position of the thick plate, which helps to ensure that the thick plates move smoothly up and down the cooling bed in sequence, maintain a stable production rhythm, and send accurate and effective position information to other systems to assist in the tracking of the thick plates, thereby improving the digitalization of steel rolling production management.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] In the attached diagram: Figure 1 A schematic diagram illustrating the implementation environment of a method for positioning a thick plate on a cooling bed according to an embodiment of the present invention; Figure 2 This is a flowchart of a method for positioning a thick plate on a cooling bed according to an embodiment of the present invention; Figure 3 This is a block diagram of a positioning device for a wide and thick plate in a cooling bed provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0019] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0021] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0022] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating the implementation environment of a method for positioning a thick plate on a cooling bed, as provided in an embodiment of the present invention.

[0023] like Figure 1 As shown, the implementation environment may include an image acquisition device 110 and a computer device 120. The computer device 120 may be at least one of a microcomputer, an embedded computer, or a neural network computer. The image acquisition device may be an industrial camera or a network camera installed above or near the outlet or inlet (target area) of the cooling bed, or an array camera installed at a specific position above the outlet or inlet (target area) of the cooling bed. Each array camera is used as the center point of a camera coordinate system, and the camera coordinate system of each array camera can be transformed to and from a preset coordinate system (world coordinate system) based on a rotation matrix and a translation vector. The industrial camera or network camera is used to detect whether the thick plate has reached the preset area of ​​the target area. If it has, the image of the thick plate is acquired by the array camera, and after masking and segmentation, it is stitched together to obtain a stitched mask image. Based on the mutual transformation between the image coordinate system of the stitched mask image, the camera coordinate system of the array camera, and the preset coordinate system, the actual center line and the actual center point coordinates under the preset coordinate system are calculated, thereby calculating the reference distance and the included angle to locate the thick plate.

[0024] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for positioning a thick plate on a cooling bed according to an embodiment of the present invention. This method can be applied to... Figure 1 The implementation environment shown can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0025] like Figure 2 As shown, in an exemplary embodiment, the method for positioning a wide and thick plate in a cooling bed includes at least steps S210 to S240, which are described in detail below: Step S210: Obtain the image of the thick plate in the target area of ​​the cold bed. The image of the thick plate is obtained based on the array camera. Perform mask segmentation on the image of the thick plate to obtain multiple segmentation mask images. Stitch the multiple segmentation mask images to obtain a stitched mask image.

[0026] In one embodiment of the present invention, before acquiring the image of the thick plate in the target area of ​​the cooling bed, the method further includes: acquiring the roller conveyor image of the target area; identifying the thick plate in the roller conveyor image to obtain a detection frame of the thick plate; comparing the detection frame with a preset area to obtain the position state of the thick plate, wherein the preset area is the area in the roller conveyor image determined according to preset vertex coordinates; if the position state is in place, then acquiring the image of the thick plate based on the array camera.

[0027] For example, the target area of ​​the cooling bed can be the cooling bed inlet or the cooling bed outlet. In this embodiment, an image acquisition device can be set around the cooling bed inlet or outlet (target area) of the 5500mm wide and thick plate production line. The image acquisition device can be installed near or above the target area according to the installation environment and shooting angle of each point. The image acquisition device can be an industrial camera or a network high-definition camera, etc. The image acquisition device can capture the roller image of all or part of the roller conveyor area of ​​the target area.

[0028] In one embodiment of the present invention, comparing the detection frame with a preset area to obtain the positioning state of the thick plate includes: obtaining a set of rectangular frames based on the center coordinates of the detection frame, the width of the detection frame, and the width of the detection frame; obtaining a set of positioning areas based on the vertex coordinates of the preset area, and calculating the cross-overlap rate between the set of rectangular frames and the set of positioning areas; if the cross-overlap rate is greater than or equal to a preset overlap rate threshold, the positioning state is in place; if the cross-overlap rate is less than the preset overlap rate threshold, the positioning state is not in place.

[0029] For example, identifying a thick plate in a roller conveyor image includes: inputting the roller conveyor image into a preset thick plate positioning recognition model. This model can determine whether the thick plate in the roller conveyor image has reached a preset area. The model obtains a detection box for the thick plate in the roller conveyor image through target recognition. The detection box can be represented by a rectangle, and the set of detection boxes is represented by the coordinates of the thick plate's center point (i.e., the center coordinates of the detection box), the length of the detection box, and its width. ,in It represents the x-coordinate of the detection box center in the image coordinate system. Let w be the y-coordinate of the detection box center in the image, and w be the width of the detection box. The height of the detection frame.

[0030] For example, the preset region is generally set as a polygon. The set of regions to be located is obtained based on the coordinates of each vertex of the preset region, which can be represented as follows: Where U represents the set of locations, Let be the coordinates of the nth vertex in the image coordinate system.

[0031] For example, determining whether a thick plate is in place based on the cross overlap rate includes: Equation (1) In equation (1), Box is the set of detection boxes, U is the set of in-place regions, and IOU is the cross-over overlap rate.

[0032] For example, a multi-frame accumulation method is used to determine whether the thick plate is in place. If the cross-overlap rate in a certain frame image is greater than or equal to a preset overlap rate threshold, the in-place status is in place, and the frame number of the in-place area is incremented by one. If the cross-overlap rate in a certain frame image is less than the preset overlap rate threshold, the in-place status is not in place. When the frame number of the in-place area is greater than a preset frame number threshold, it is determined that the thick plate has been in place.

[0033] In one embodiment of the present invention, a wide and thick plate image is segmented by masking to obtain multiple segmentation mask images. The multiple segmentation mask images are then stitched together to obtain a stitched mask image. This process includes: scaling, translating, and rotating the multiple segmentation mask images based on preset scaling factors, preset translation parameters, and preset rotation parameters to obtain multiple processed segmentation mask images; stitching the processed multiple segmentation mask images based on corresponding preset stitching weights; and performing a convolution operation on the stitched image to obtain the stitched mask image.

[0034] For example, multiple segmentation mask images obtained by scaling, translating, and rotating multiple segmentation mask images based on preset scaling factors, preset translation parameters, and preset rotation parameters include: Equation (2) Equation (3) In equation (2), To segment the original point coordinates in the mask image, These are the coordinates of points obtained after rotation, translation, and scaling in the segmentation mask image, where 's' is a preset scaling factor. Preset rotation parameters, These are the preset translation parameters.

[0035] In equation (3), This is the segmentation mask image corresponding to the j-th array camera after processing. yes The corresponding preset stitching weights, where M is the stitched image.

[0036] For example, the stitched image M is based on a standard deviation of A Gaussian kernel is used for convolution to obtain a stitched mask image. .

[0037] Step S220: Extract the center line and center point coordinates of the thick plate in the stitching mask image as the image center line and image center point. Based on the camera parameters of the array camera, transform the image center line and image center point coordinates to a preset coordinate system to obtain the actual center line and actual center point coordinates respectively.

[0038] In one embodiment of the present invention, transforming the image centerline and image center point coordinates to a preset coordinate system based on the camera parameters of the array camera includes: obtaining the aperture center coordinates of the array camera's aperture center point in the preset coordinate system, and a first distance from the edge of the thick plate to the array camera, wherein the camera parameters include at least the focal length; converting the image center point coordinates to actual center point coordinates in the preset coordinate system based on the first distance, focal length, and aperture center coordinates; converting the coordinates of any two points on the image centerline to actual coordinates of the two points in the preset coordinate system based on the first distance, focal length, and aperture center coordinates; and determining the actual centerline based on the actual coordinates of the two points.

[0039] For example, based on the camera parameters of the array camera, the coordinates of the image center line and the image center point are transformed to a preset coordinate system to obtain the actual center line and the actual center point coordinates, respectively: Equation (4) In equation (4), ( , (This is a spliced ​​mask image) The point in the middle, It is the coordinate of the aperture center point of the j-th camera in the preset coordinate system. Let j be the focal length of the j-th array camera. Let the first distance from the thick plate to the j-th camera be ( (This is a spliced ​​mask image) The coordinates of point p in the camera coordinate system, R is the preset rotation matrix, and T is the preset translation vector. , , (This is a spliced ​​mask image) The coordinates of point p in the preset coordinate system (i.e., the world coordinate system).

[0040] Step S230: Calculate the reference distance between the thick plate and the roller conveyor based on the preset direction vector of the roller conveyor in the target area and the actual center point coordinates, and calculate the angle between the thick plate and the edge line of the roller conveyor based on the actual center line.

[0041] In one embodiment of the present invention, calculating the angle between the thick plate and the edge line of the roller conveyor based on the actual center line includes: calculating the angle between the thick plate and the edge line of the roller conveyor based on the inverse cosine function and the actual coordinates of the two points.

[0042] For example, calculating the reference distance between the thick plate and the roller conveyor, and calculating the angle between the thick plate and the edge line of the roller conveyor based on the actual centerline, includes: Equation (5) Equation (6) In equations (5) and (6), d is the angle between the thick plate and the edge line of the roller conveyor (i.e., the angle between the actual center line and the edge line of the roller conveyor), and d is the reference distance between the thick plate and the roller conveyor (i.e., the distance from the center point of the front end of the thick plate to the edge line of the roller conveyor). and These are the coordinates of any two points on the actual center line in the world coordinate system (preset coordinate system). These are the actual center point coordinates. It is the coordinate of any point r on the roller conveyor in the preset coordinate system. It is the set direction vector of the roller conveyor.

[0043] For example, the angle between the actual centerline and the edge line of the roller conveyor is the angle between the thick plate and the inlet or outlet (target area) roller conveyor of the cooling bed. This angle includes, but is not limited to, the horizontal angle formed by the parallel centerline (actual centerline) of the long side of the thick plate and the inlet or outlet roller conveyor of the cooling bed.

[0044] For example, the reference distance between the thick plate and the roller conveyor is the distance between the thick plate and a specific reference position of the roller conveyor at the inlet or outlet (target area) of the cooling bed. The reference position can be any position on the roller conveyor at the inlet or outlet (target area) of the cooling bed, and the reference distance can be the length of the vertical line segment between the center point (actual center point coordinates) of the front or rear end of the thick plate and the reference position (point r).

[0045] Step S240: Obtain the positioning result of the thick plate in the target area based on the included angle and the reference distance, and trigger an alarm when there is an abnormality in the positioning result.

[0046] In one embodiment of the present invention, the positioning result of the thick plate in the target area is obtained based on the included angle and the reference distance, and an alarm is triggered when the positioning result is abnormal. The alarm is triggered as follows: if the included angle is greater than a preset included angle threshold, the positioning result is abnormal and an included angle abnormality alarm is triggered; if the reference distance is not within the preset distance range, the positioning result is abnormal and a reference distance abnormality alarm is triggered.

[0047] Please see Figure 3 , Figure 3 This is a block diagram of a positioning device for a thick cooling bed plate according to an embodiment of the present invention. This device can be applied to... Figure 1 The implementation environment shown can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0048] like Figure 3 As shown, the exemplary cold bed thick plate positioning device includes: The image stitching module 310 is used to acquire the image of the wide and thick plate in the target area of ​​the cold bed. The image of the wide and thick plate is acquired based on the array camera. The image of the wide and thick plate is segmented by mask to obtain multiple segmentation mask images. The multiple segmentation mask images are stitched together to obtain a stitched mask image. The coordinate transformation module 320 is used to extract the center line and center point coordinates of the thick plate in the stitched mask image as the image center line and image center point. According to the camera parameters of the array camera, the image center line and image center point coordinates are transformed to the preset coordinate system to obtain the actual center line and actual center point coordinates respectively. The position calculation module 330 is used to calculate the reference distance between the thick plate and the roller conveyor based on the preset direction vector of the roller conveyor in the target area and the actual center point coordinates, and to calculate the angle between the thick plate and the edge line of the roller conveyor based on the actual center line. The positioning alarm module 340 is used to obtain the positioning result of the thick plate in the target area based on the included angle and the reference distance, and to trigger an alarm when there is an abnormality in the positioning result.

[0049] Before the image stitching module 310 acquires the image of the thick plate in the target area of ​​the cooling bed, it further includes: acquiring the roller conveyor image of the target area, identifying the thick plate in the roller conveyor image to obtain the detection frame of the thick plate; comparing the detection frame with a preset area to obtain the position status of the thick plate, wherein the preset area is the area in the roller conveyor image determined according to the preset vertex coordinates; if the position status is in place, then acquiring the image of the thick plate based on the array camera.

[0050] The image stitching module 310 compares the detection box with the preset area to obtain the positioning status of the thick plate, including: obtaining a set of rectangular boxes based on the center coordinates of the detection box, the width of the detection box, and the detection box width; obtaining a set of positioning areas based on the vertex coordinates of the preset area, and calculating the cross-overlap rate between the set of rectangular boxes and the set of positioning areas; if the cross-overlap rate is greater than or equal to the preset overlap rate threshold, the positioning status is in place; if the cross-overlap rate is less than the preset overlap rate threshold, the positioning status is not in place.

[0051] The image stitching module 310 performs mask segmentation on the wide and thick plate image to obtain multiple segmentation mask images, and stitches the multiple segmentation mask images to obtain a stitched mask image. This includes: scaling, translating, and rotating the multiple segmentation mask images based on preset scaling factors, preset translation parameters, and preset rotation parameters to obtain multiple processed segmentation mask images; stitching the multiple processed segmentation mask images based on corresponding preset stitching weights; and performing a convolution operation on the stitched image to obtain the stitched mask image.

[0052] The coordinate transformation module 320 transforms the coordinates of the image centerline and the image center point to a preset coordinate system based on the camera parameters of the array camera. This includes: obtaining the aperture center coordinates of the array camera's aperture center point in the preset coordinate system, and the first distance from the edge of the thick plate to the array camera, where the camera parameters include at least the focal length; converting the image center point coordinates to the actual center point coordinates in the preset coordinate system based on the first distance, focal length, and aperture center coordinates; converting the coordinates of any two points on the image centerline to the actual coordinates of the two points in the preset coordinate system based on the first distance, focal length, and aperture center coordinates; and determining the actual centerline based on the actual coordinates of the two points.

[0053] The position calculation module 330 calculates the angle between the thick plate and the edge line of the roller conveyor based on the actual center line, including: calculating the angle between the thick plate and the edge line of the roller conveyor based on the inverse cosine function and the actual coordinates of two points.

[0054] The positioning alarm module 340 obtains the positioning result of the thick plate in the target area based on the included angle and the reference distance, and triggers an alarm when there is an abnormality in the positioning result, including: if the included angle is greater than the preset included angle threshold, the positioning result has an abnormal included angle and triggers an included angle abnormality alarm; if the reference distance is not within the preset distance range, the positioning result has an abnormal reference distance and triggers a reference distance abnormality alarm.

[0055] The aforementioned device applies image recognition and deep learning technologies to the cooling bed of the steel rolling production line, enabling precise positioning of each thick plate. This helps personnel quickly and accurately identify and correct any positional anomalies, solving the problem of the inability to quantitatively and accurately determine the position of thick plates. It helps ensure that thick plates move smoothly up and down the cooling bed in sequence, maintaining a stable production rhythm. The accurate and effective positional information is sent to other systems to assist in tracking the thick plates, thereby improving the digitalization of steel rolling production management.

[0056] It is understood that the cold bed thick plate positioning device and the cold bed thick plate positioning method provided in the above embodiments belong to the same concept. The specific operation of the cold bed thick plate positioning method has been described in detail in the above embodiments and will not be repeated here. In practical applications, the cold bed thick plate positioning device provided in the above embodiments can be assigned to different functional modules as needed. That is, the internal structure of the cold bed thick plate positioning device can be divided into different functional modules, and then all or part of the functions of the corresponding functional modules can be implemented by the cold bed thick plate positioning method described in the above embodiments. No specific limitation is made here. For example, the image stitching module 310 includes steps for executing step S210 and related steps, the coordinate transformation module 320 includes steps for executing step S220 and related steps, the position calculation module 330 includes steps for executing step S230 and related steps, and the positioning alarm module 340 includes steps for executing step S240 and related steps.

[0057] Figure 4 This is a schematic diagram of an electronic device provided in one embodiment of the present invention. It should be noted that... Figure 4 The computer system 400 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0058] like Figure 4 As shown, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 402 or loaded from Storage Unit 408 into Random Access Memory (RAM) 403, such as performing the methods described in the above embodiments. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0059] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 410 as needed so that computer programs read from it can be installed into storage section 408 as needed.

[0060] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs various functions defined in the system of the present invention.

[0061] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0062] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0063] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0064] Another aspect of the present invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the cold bed thick plate positioning method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0065] Another aspect of the present invention provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the cold bed thick plate positioning method provided in the various embodiments described above.

[0066] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for positioning a thick plate on a cooling bed, characterized in that, The method includes: A wide and thick plate image of the target area of ​​the cooling bed is acquired. The wide and thick plate image is acquired based on an array camera. The wide and thick plate image is segmented by masking to obtain multiple segmentation mask images. The multiple segmentation mask images are then stitched together to obtain a stitched mask image. The center line and center point coordinates of the thick plate in the stitched mask image are extracted as the image center line and image center point. According to the camera parameters of the array camera, the coordinates of the image center line and the image center point are transformed to a preset coordinate system to obtain the actual center line and actual center point coordinates respectively. Based on the preset direction vector of the roller conveyor in the target area and the actual center point coordinates, the reference distance between the thick plate and the roller conveyor is calculated, and the angle between the thick plate and the edge line of the roller conveyor is calculated based on the actual center line. The positioning result of the thick plate within the target area is obtained based on the included angle and the reference distance, and an alarm is triggered when there is an abnormality in the positioning result.

2. The method for positioning a thick plate on a cooling bed according to claim 1, characterized in that, Before acquiring the image of the thick plate in the target area of ​​the cooling bed, the following steps are also included: Obtain an image of the roller conveyor in the target area, identify the thick plate in the roller conveyor image, and obtain a detection box for the thick plate; The detection frame is compared with a preset area to obtain the positioning status of the thick plate. The preset area is the area in the roller conveyor image determined according to preset vertex coordinates. If the positioning status is "in position", then the image of the thick plate is acquired based on the array camera.

3. The method for positioning a thick plate on a cooling bed according to claim 2, characterized in that, The detection frame is compared with a preset area to obtain the positioning status of the thick plate, including: A set of rectangular frames is obtained based on the center coordinates of the detection frame, the width of the detection frame, and the detection frame width. The set of placement areas is obtained based on the vertex coordinates of the preset area, and the overlap rate between the set of rectangles and the set of placement areas is calculated. If the cross-overlap rate is greater than or equal to a preset overlap rate threshold, then the positioning status is in place; If the cross-overlap rate is less than the preset overlap rate threshold, then the "in place" status is "not in place".

4. The method for positioning a thick plate on a cooling bed according to any one of claims 1-3, characterized in that, The image of the wide and thick plate is segmented using a mask to obtain multiple segmentation mask images. These multiple segmentation mask images are then stitched together to obtain a stitched mask image, which includes: Multiple segmentation mask images are obtained by scaling, translating, and rotating the multiple segmentation mask images based on preset scaling factors, preset translation parameters, and preset rotation parameters; The processed multiple segmentation mask images are stitched together based on corresponding preset stitching weights, and the stitched image is then convolved to obtain the stitched mask image.

5. The method for positioning a thick plate on a cooling bed according to any one of claims 1-3, characterized in that, Transforming the image centerline and the coordinates of the image center point to a preset coordinate system based on the camera parameters of the array camera includes: Obtain the aperture center coordinates of the array camera in the preset coordinate system, and the first distance from the edge of the thick plate to the array camera. The camera parameters include at least the focal length. Based on the first distance, the focal length, and the aperture center coordinates, the image center point coordinates are converted into the actual center point coordinates in the preset coordinate system; The coordinates of any two points in the center line of the image are converted into the actual coordinates of the two points in the preset coordinate system based on the first distance, the focal length, and the aperture center coordinates. The actual centerline is determined based on the actual coordinates of the two points.

6. The method for positioning a thick plate on a cooling bed according to claim 5, characterized in that, And the angle between the thick plate and the edge line of the roller conveyor is calculated based on the actual center line, including: The angle between the thick plate and the edge line of the roller conveyor is calculated based on the inverse cosine function and the actual coordinates of the two points.

7. The method for positioning a thick plate on a cooling bed according to any one of claims 1-3, characterized in that, The positioning result of the thick plate within the target area is obtained based on the included angle and the reference distance, and an alarm is triggered when the positioning result is abnormal, including: If the included angle is greater than a preset included angle threshold, the positioning result shows an abnormal included angle, triggering an abnormal included angle alarm. If the reference distance is not within the preset distance range, the positioning result indicates a reference distance anomaly, triggering a reference distance anomaly alarm.

8. A positioning device for a thick plate on a cooling bed, characterized in that, The device includes: An image stitching module is used to acquire a wide and thick plate image of the target area of ​​the cold bed. The wide and thick plate image is acquired based on an array camera. The wide and thick plate image is segmented by a mask to obtain multiple segmentation mask images. The multiple segmentation mask images are stitched together to obtain a stitched mask image. The coordinate transformation module is used to extract the center line and center point coordinates of the thick plate in the stitched mask image as the image center line and image center point. According to the camera parameters of the array camera, the coordinates of the image center line and the image center point are transformed to a preset coordinate system to obtain the actual center line and actual center point coordinates respectively. The position calculation module is used to calculate the reference distance between the thick plate and the roller conveyor based on the preset direction vector of the roller conveyor in the target area and the actual center point coordinates, and to calculate the angle between the thick plate and the edge line of the roller conveyor based on the actual center line. The positioning alarm module is used to obtain the positioning result of the thick plate in the target area based on the included angle and the reference distance, and to trigger an alarm when the positioning result is abnormal.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the cold bed thick plate positioning method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by the computer's processor, causes the computer to perform the cold bed thick plate positioning method as described in any one of claims 1-7.

Images