Steel plate flatness detection method and system, medium and electronic equipment

Abstract

The invention provides a steel plate flatness detection method. The steel plate flatness detection method comprises the following steps: constructing a camera non-overlapping view field area by using a plurality of industrial cameras, and projecting laser stripes by using a laser transmitter; performing image acquisition on the surface of the steel plate covered with the laser stripes to obtain local images of the surface of the steel plate in view angle areas of the industrial cameras; processing the local image of the surface of the steel plate to obtain a three-dimensional point cloud of the surface of the steel plate; and the flatness of the local areas of the multiple steel plate surfaces is obtained based on the three-dimensional point clouds of the steel plate surfaces. According to the steel plate flatness detection method, automatic detection of the surface flatness of the steel plate can be realized, and the detection precision of the surface flatness of the steel plate is improved.

Description

Technical Field

[0001] This application belongs to the field of steel plate flatness detection technology, and relates to a steel plate flatness detection method, system, medium and electronic equipment. Background Technology

[0002] In recent years, the demand for modern steel plate industrial production has been increasing. In many applications, the flatness of steel plates directly affects their performance. For example, the flatness of building structures can affect their stability and durability, while the flatness of steel plates in automobile manufacturing can affect vehicle safety and fuel efficiency. Therefore, automated inspection of the flatness of large-size steel plates is necessary. The flatness of a steel plate surface reflects the average unevenness of the steel surface in the length and width directions according to specified standards. It is one of the important indicators of steel plate quality. Commonly, steel plate flatness is measured by linear flatness, curved flatness, and corrugated flatness. If the steel plate is uneven, it may cause problems during processing or welding, leading to inaccurate dimensions or unreasonable shapes in the manufactured products, ultimately affecting product performance and reliability. Flat steel plates are easier to machine, cut, weld, and form, while uneven steel plates may require more processing steps to adjust their shape, which increases manufacturing costs and prolongs manufacturing time. In steel structure and welding applications, flatness is also crucial to the quality of welds. Uneven steel plate surfaces can lead to uneven welds, thereby reducing weld quality and increasing the risk of weld cracks. Summary of the Invention

[0003] The purpose of this application is to provide a method, system, medium, and electronic equipment for detecting the flatness of steel plates, which can realize the automatic detection of the flatness of steel plate surfaces and improve the detection accuracy of the flatness of steel plate surfaces.

[0004] In a first aspect, this application provides a method for detecting the flatness of a steel plate. The method includes: constructing a non-overlapping field of view using multiple industrial cameras; projecting laser stripes using a laser emitter; acquiring images of the steel plate surface covering the laser stripes to obtain local images of the steel plate surface in the field of view of each of the industrial cameras; processing the local images of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface; and obtaining the flatness of multiple local areas of the steel plate surface based on the three-dimensional point cloud of the steel plate surface.

[0005] In one implementation of the first aspect, the process of processing a local image of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface includes: preprocessing the local image of the steel plate surface to obtain a preprocessed local image of the steel plate surface; extracting the laser stripe center lines from the preprocessed local image of the steel plate surface to obtain laser center point clouds of each of the industrial camera's viewpoint regions; and stitching together the laser center point clouds of each of the industrial camera's viewpoint regions to obtain a three-dimensional point cloud of the steel plate surface.

[0006] In one implementation of the first aspect, the process of obtaining the laser center point cloud of the viewing area of ​​each of the industrial cameras further includes: performing single-target positioning on the industrial cameras to obtain the internal parameters of each industrial camera; performing multi-target positioning on the industrial cameras to obtain the relative attitude between the multiple industrial cameras; and performing coordinate transformation on the laser line midline point of the viewing area of ​​each of the industrial cameras based on the internal parameters and the relative attitude to obtain the laser center point cloud of the viewing area of ​​each of the industrial cameras.

[0007] In one implementation of the first aspect, the process of obtaining the flatness of multiple local areas of the steel plate surface based on the three-dimensional point cloud of the steel plate surface includes: fitting and updating the coordinate points in the laser center point cloud to obtain the standard plane equation of the steel plate reference surface; partitioning the three-dimensional point cloud of the steel plate surface to obtain multiple local area point clouds of the steel plate surface; and obtaining the flatness of the multiple local area point clouds of the steel plate surface and the standard plane equation.

[0008] In one implementation of the first aspect, the process of fitting and updating the coordinate points in the laser center point cloud to obtain the standard plane equation of the steel plate reference surface includes: obtaining a first coordinate point, a second coordinate point, and a third coordinate point, wherein the first coordinate point, the second coordinate point, and the third coordinate point are three points in the laser center point cloud that are not on the same straight line; fitting the first coordinate point, the second coordinate point, and the third coordinate point into a reference plane equation; and updating and correcting the reference plane equation using the remaining coordinate points in the laser center point cloud to obtain the standard plane equation.

[0009] In one implementation of the first aspect, the process of obtaining the flatness of the multiple local areas of the steel plate surface based on the point cloud of the multiple local areas of the steel plate surface and the standard plane equation includes: obtaining the distance from the center point of the laser stripe in the point cloud of the multiple local areas of the steel plate surface to the center point of the standard plane equation; and obtaining the flatness of the multiple local areas of the steel plate surface based on the center point distance.

[0010] In one implementation of the first aspect, the steel plate flatness detection method further includes: comparing the flatness of multiple local areas on the surface of the steel plate with a flatness threshold, and obtaining the flatness state of the steel plate surface based on the comparison result.

[0011] Secondly, this application provides a steel plate flatness detection system, which includes: a preparation module for constructing a non-overlapping field of view using multiple industrial cameras and projecting laser stripes using a laser emitter; an image acquisition module for acquiring images of the steel plate surface covering the laser stripes to obtain local images of the steel plate surface in the viewing areas of each of the industrial cameras; an image processing module for processing the local images of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface; and a flatness acquisition module for obtaining the flatness of multiple local areas of the steel plate surface based on the three-dimensional point cloud of the steel plate surface.

[0012] Thirdly, this application provides an electronic device, the electronic device comprising: a memory storing a computer program thereon; and a processor communicatively connected to the memory for executing the computer program to implement the above-described steel plate flatness detection method.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, characterized in that the program, when executed by an electronic device, implements the above-described method for detecting the flatness of a steel plate.

[0014] As described above, the steel plate flatness detection method, system, medium, and electronic equipment described in this application have the following beneficial effects:

[0015] The steel plate surface flatness detection method provided in this application can acquire images of the steel plate surface with projected laser stripes based on the non-overlapping camera area, and process the local images of the steel plate surface in each camera view area to obtain the flatness of multiple local areas of the steel plate surface. This method enables automatic detection of steel plate surface flatness and improves the detection accuracy. Attached Figure Description

[0016] Figure 1 The diagram shows an application scenario of the steel plate flatness detection method described in this application embodiment.

[0017] Figure 2 The diagram shown is a structural schematic of the camera protection device described in an embodiment of this application.

[0018] Figure 3 The diagram shown is a structural schematic of the laser protection device described in an embodiment of this application.

[0019] Figure 4The diagram shows a process schematic of the steel plate flatness detection method described in the embodiments of this application.

[0020] Figure 5 The diagram shown is a structural schematic of the non-overlapping field of view of the camera as described in an embodiment of this application.

[0021] Figure 6 The diagram shows a schematic representation of the process of projecting laser stripes onto a reference surface as described in an embodiment of this application.

[0022] Figure 7 The diagram shows a process of projecting laser stripes onto the surface of a steel plate as described in an embodiment of this application.

[0023] Figure 8 The diagram shows a process of projecting laser stripes onto the surface of a steel plate as described in an embodiment of this application.

[0024] Figure 9 The diagram shows the process of obtaining a three-dimensional point cloud of a steel plate surface as described in an embodiment of this application.

[0025] Figure 10 The diagram shown is a schematic representation of the process of obtaining the laser center point cloud as described in an embodiment of this application.

[0026] Figure 11 The diagram shown is a structural schematic of the steel plate flatness detection model described in the embodiments of this application.

[0027] Figure 12 The diagram shows a process for obtaining the flatness of multiple local areas on the surface of steel plates as described in an embodiment of this application.

[0028] Figure 13 This is a schematic diagram illustrating the process of obtaining the standard plane equation of the steel plate reference surface as described in an embodiment of this application.

[0029] Figure 14 The diagram shows a process for obtaining the flatness of multiple local areas on the surface of steel plates as described in an embodiment of this application.

[0030] Figure 15 The image shown is a schematic diagram illustrating the result of three-dimensional point cloud reconstruction as described in the embodiments of this application.

[0031] Figure 16 The diagram shown is a schematic representation of the real-time flatness results described in the embodiments of this application.

[0032] Figure 17 The diagram shown is a structural schematic of the steel plate flatness detection system described in this application embodiment.

[0033] Figure 18 The diagram shown is a structural schematic of the electronic device described in an embodiment of this application.

[0034] Component designation explanation

[0035] 1. Steel Plate Flatness Detection System

[0036] 11 Preparation Module

[0037] 12 Image Acquisition Module

[0038] 13 Image Processing Module

[0039] 14. Flatness Acquisition Module

[0040] 2 Electronic devices

[0041] 21. Memory

[0042] 22 processors

[0043] 23 Monitors

[0044] Steps S11 to S14

[0045] Steps S21 to S22

[0046] Steps S31 to S34

[0047] Steps S41 to S43

[0048] Steps S51 to S53

[0049] Steps S61 to S62 Detailed Implementation

[0050] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0051] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application 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.

[0052] In recent years, the demand for modern steel plate industrial production has been increasing. In many applications, the flatness of steel plates directly affects their performance. For example, the flatness of building structures can affect their stability and durability, while the flatness of steel plates in automobile manufacturing can affect vehicle safety and fuel efficiency. Therefore, automated inspection of the flatness of large-size steel plates is necessary. The flatness of a steel plate surface reflects the average unevenness of the steel surface in the length and width directions according to specified standards. It is one of the important indicators of steel plate quality. Commonly, steel plate flatness is measured by linear flatness, curved flatness, and corrugated flatness. If the steel plate is uneven, it may cause problems during processing or welding, leading to inaccurate dimensions or unreasonable shapes in the manufactured products, ultimately affecting product performance and reliability. Flat steel plates are easier to machine, cut, weld, and form, while uneven steel plates may require more processing steps to adjust their shape, which increases manufacturing costs and prolongs manufacturing time. In steel structure and welding applications, flatness is also crucial to the quality of welds. Uneven steel plate surfaces can lead to uneven welds, thereby reducing weld quality and increasing the risk of weld cracks.

[0053] Traditional inspection methods mainly rely on manual labor or mechanical thickness gauges. However, manual monitoring is time-consuming and labor-intensive, making it difficult to meet the needs of large-scale production. Furthermore, mechanical thickness gauges are limited by probe size and measurement principles, making it difficult to accurately measure the undulations of the steel plate surface. These methods are insufficient for comprehensive inspection of the steel plate surface, easily missing local defects, resulting in low work efficiency and low inspection accuracy.

[0054] To address at least the aforementioned problems, this application provides a method for detecting the flatness of steel plates, as illustrated in the following embodiments. The technical solutions in these embodiments will be described in detail below with reference to the accompanying drawings.

[0055] Figure 1 This diagram illustrates an application scenario according to an embodiment of this application. For example... Figure 1 As shown, the steel plate flatness detection device includes: a plate press, a steel plate, multiple industrial cameras, multiple laser emitters, a light source, a first connecting assembly, a second connecting assembly, camera protection devices, laser protection devices, a PLC, and an industrial touch screen display. Please refer to [link / reference]. Figure 2 The camera protection device includes a first fixed bracket and a camera protective housing. (See also...) Figure 3 The laser protection device includes a second fixed bracket and a laser emitter protective shell.

[0056] The industrial camera is fixed to the first fixed bracket, and the industrial camera and the first fixed bracket are disposed inside the camera protective housing; the camera protective housing is connected to the first connecting assembly, and the first connecting assembly is fixed to the wall beam. The laser emitter is fixed to the second fixed bracket, and the laser emitter and the second fixed bracket are disposed inside the laser emitter protective housing; the laser emitter protective housing is connected to the second connecting assembly, and the second connecting assembly is fixed to the beam. The PLC is connected to the industrial camera and the laser emitter for controlling the industrial camera and / or the laser emitter. An industrial touch screen is used to display the calibration results of the industrial camera and the flatness detection results of the steel plate.

[0057] For example, the first connecting component and the second connecting component can be gimbals. Gimbals are used to achieve angle adjustment of industrial cameras and laser emitters.

[0058] Specifically, each industrial camera is fixed to a designated position on the crossbeam via a first connecting assembly. The camera and laser protection devices prevent equipment damage in the complex environment of the steel plate flattening process, reducing the risk of damage. They also effectively prevent dust contamination of the cameras and lasers, as well as external impacts, ensuring the equipment's operational performance.

[0059] Figure 4 This is a schematic diagram illustrating the process of a steel plate flatness detection method according to an embodiment of this application. Figure 4 As shown, the method for detecting the flatness of steel plates includes:

[0060] S11 uses multiple industrial cameras to construct a non-overlapping field of view and uses a laser emitter to project laser stripes.

[0061] For example, when there are four industrial cameras, a non-overlapping field of view is constructed using these four cameras. The non-overlapping field of view of the cameras can be 5m*5m. Please refer to the schematic diagram of the non-overlapping field of view of the cameras. Figure 5 Within a 5m*5m field of view, the viewing area of ​​each camera is 2.5m*2.5m.

[0062] Furthermore, once the non-overlapping field of view of the camera is constructed, the size of the camera's field of view is also fixed. The constructed non-overlapping field of view of the camera can detect the flatness of steel plate surfaces of any size.

[0063] In one embodiment of this application, projecting laser stripes using a laser emitter includes projecting laser stripes onto a reference plane and projecting laser stripes onto the surface of a steel plate. See also... Figure 6The process of projecting laser stripes onto a reference plane includes: before the steel plate enters the camera's field of view, a laser emitter reflects purple laser stripes onto the reference plane at a certain angle, with each laser stripe spaced 20cm apart. Please refer to [link to relevant documentation]. Figure 7 and Figure 8 The process of projecting laser stripes onto the steel plate surface includes projecting purple laser stripes and green intersecting laser stripes onto the steel plate surface, respectively. It should be noted that the order in which the purple laser stripes and the green intersecting laser stripes are projected is not important.

[0064] S12, image acquisition is performed on the steel plate surface covered with laser stripes to obtain local images of the steel plate surface in the viewing area of ​​each industrial camera.

[0065] For example, after the system starts running, the PLC (Programmable Logic Controller) enters the working state, controlling the emission of the laser emitter and the image acquisition of the industrial camera. Before the steel plate enters the non-overlapping field of view of the camera, purple laser stripes are projected onto a reference plane using the laser emitter. By acquiring images of the reference plane, laser calibration is performed on the reference plane to reconstruct the three-dimensional data information of the steel plate's reference plane, thereby constructing a flatness standard plane. While waiting for the steel plate to enter the non-overlapping field of view of the camera, when the steel plate is within the camera's non-overlapping field of view, laser stripes and intersecting laser stripes are projected onto the camera's non-overlapping field of view, and images of the projected steel plate surface are acquired to obtain local images of the steel plate surface in each camera's viewing angle region.

[0066] S13, process the local image of the steel plate surface to obtain the three-dimensional point cloud of the steel plate surface.

[0067] S14, obtain the flatness of multiple local areas on the surface of the steel plate based on the three-dimensional point cloud of the steel plate surface.

[0068] As described above, the steel plate surface flatness detection method provided in this application can acquire images of the steel plate surface with projected laser stripes based on the non-overlapping camera area, and process the local images of the steel plate surface in each camera's viewpoint area to determine the flatness of multiple local areas of the steel plate surface. This method enables automatic detection of steel plate surface flatness and improves the accuracy of the flatness detection.

[0069] Figure 9 This is a schematic diagram illustrating the process of obtaining a three-dimensional point cloud of a steel plate surface in one embodiment of this application. For example... Figure 9 As shown, the process of processing a local image of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface includes:

[0070] S21, preprocess the local image of the steel plate surface to obtain a preprocessed local image of the steel plate surface.

[0071] For example, the preprocessing method includes performing edge detection processing on the local image of the steel plate surface to extract the ROI region of the local image of the steel plate surface; and performing noise reduction processing on the local image of the steel plate surface to eliminate noise generated by the surrounding environment on the laser stripes. By preprocessing the local image of the steel plate surface, the region of the laser stripes and the width of each row of laser stripes can be further obtained.

[0072] S22, extract the center line of the laser stripe from the preprocessed local image of the steel plate surface to obtain the laser center point cloud of each industrial camera's field of view area.

[0073] Specifically, the center line extraction algorithm is used to extract the center of the structured light stripes in the local image of the preprocessed steel plate surface to obtain the position of the laser stripe center line in the local image of the preprocessed steel plate surface.

[0074] For example, the stripe centerline extraction algorithm can be the Steger algorithm for sub-pixel level light stripe centerlines based on the Hessian matrix. The normal direction of the light stripe is obtained through the Hessian matrix, and a Taylor polynomial expansion is applied to the pixel grayscale along the normal direction to obtain the grayscale distribution function, and then the sub-pixel position of the laser stripe centerline is obtained.

[0075] Please continue reading Figure 10 The process of obtaining the laser center point cloud of each industrial camera's field of view also includes:

[0076] S31, perform single-target positioning on the industrial cameras to obtain the internal parameters of each industrial camera. The internal parameters include the camera focal length f and the principal point coordinates (u0, v0).

[0077] S32, perform multi-target positioning on the industrial cameras to obtain the relative attitudes between the multiple industrial cameras.

[0078] S33, based on the internal parameters and the relative attitude, perform coordinate transformation on the laser line center point of each industrial camera's field of view to obtain the laser center point cloud of each industrial camera's field of view.

[0079] For example, after denoising and center region extraction processing is performed on a local image of the steel plate surface covered with laser stripes, a processed local image of the steel plate surface is obtained. The center lines of the laser stripes are then extracted from the processed local image to obtain the sub-pixel positions of the center lines of each laser stripe in the local image. Then, based on the internal parameters after camera calibration and the relative attitudes between the industrial cameras, the sub-pixel position coordinates of the laser stripe center lines are converted into world coordinates to obtain the three-dimensional coordinates of each laser stripe center in the world coordinate system. After restoring the three-dimensional coordinates, the laser center point cloud of the view area of ​​each industrial camera is obtained.

[0080] S34, stitch together the laser center point cloud of each of the industrial camera's field of view to obtain a three-dimensional point cloud on the surface of the steel plate.

[0081] Figure 11 The diagram shown is a structural schematic of a steel plate flatness detection model according to an embodiment of this application. Figure 11 As shown, the process of obtaining the overall point cloud of the actual surface of the steel plate includes:

[0082] If the two-dimensional pixel laser point under the view of a certain camera is n = 1, 2, 3, 4, where n represents the field of view of the nth camera, i represents the i-th laser line in the field of view of that camera, and j represents the center point of the j-th laser line in the i-th laser line. For the field of view of the nth camera (n = 1, 2, 3, 4), the plane equation of the laser plane in the corresponding camera coordinate system is obtained by fitting the coordinates of all laser center points on the i-th laser line (i = 1, 2, ..., 12), thus obtaining the depth of the pixels on the laser line. The equation of the laser plane corresponding to the nth camera is expressed as:

[0083] A n x+B n y+C n z+D n =0

[0084] By transforming the intrinsic parameter matrix obtained after single-target positioning of the camera, the three-dimensional camera coordinates (X, Y, F, G, I) corresponding to the camera's viewpoint can be obtained. c ,Y c Z c The coordinate transformation relationship is expressed as:

[0085]

[0086] The laser center point cloud from the perspective of each camera is obtained based on the external parameter matrix obtained after multi-target calibration among each camera. n = 1, 2, 3, 4:

[0087]

[0088] Taking the main camera in the non-overlapping field of view as camera 1, the relative rotation and translation matrices of the other three cameras relative to the main camera 1 are obtained based on the extrinsic parameter matrix of the multi-camera calibration. 1m ,T 1m [m = 2, 3, 4]. The 3D camera coordinates from each camera's viewpoint are reconstructed to obtain the corresponding 3D point cloud. n = 1, 2, 3, 4. Using the camera coordinate system formed by camera 1 as the global coordinate system, the four sets of point clouds are stitched together to obtain the overall point cloud P of the actual surface of the steel plate. w [X w ,Y w Z w ].

[0089]

[0090] Figure 12 This diagram illustrates the process of obtaining the flatness of multiple local areas on the surface of steel plates in one embodiment of this application. Figure 12 As shown, the process of obtaining the flatness of multiple local areas on the surface of the steel plate based on the three-dimensional point cloud of the steel plate surface includes:

[0091] S41, Fit and update the coordinates of the laser center point cloud to obtain the standard plane equation of the steel plate reference surface.

[0092] S42, the three-dimensional point cloud on the surface of the steel plate is partitioned to obtain multiple local point clouds on the surface of the steel plate.

[0093] Specifically, the process of partitioning the 3D point cloud on the steel plate surface includes: projecting green intersecting laser stripes onto the steel plate surface, dividing the 5m*5m steel plate surface within the camera's field of view into 25 small 1m*1m areas. A schematic diagram of the steel plate surface positioning and partitioning can be found here. Figure 8 The overall three-dimensional point cloud P on the steel plate surface is obtained based on the green intersecting laser stripes. w [X w ,Y w Z w The point cloud was divided into 25 regions. λ = 1, 2, ..., 25.

[0094] S43, obtain the flatness of the local areas of the multiple steel plate surfaces based on the point cloud of the local areas of the multiple steel plate surfaces and the standard plane equation.

[0095] Figure 13 This is a schematic diagram illustrating the process of obtaining the standard plane equation of the steel plate reference surface in one embodiment of this application. For example... Figure 13As shown, the process of fitting and updating the coordinates of the laser center point cloud to obtain the standard plane equation of the steel plate reference surface includes:

[0096] S51, obtain the first coordinate point, the second coordinate point, and the third coordinate point, wherein the first coordinate point, the second coordinate point, and the third coordinate point are three points in the laser center point point cloud that are not on the same straight line.

[0097] S52, fit the first coordinate point, the second coordinate point and the third coordinate point into a reference plane equation.

[0098] S53, the reference plane equation is updated and corrected using the remaining coordinate points in the laser center point cloud to obtain the standard plane equation.

[0099] For example, the standard plane equation W is expressed as:

[0100] Ax + By + Cz + 1 = 0

[0101] Figure 14 This diagram illustrates the process of obtaining the flatness of multiple local areas on the surface of steel plates in one embodiment of this application. Figure 14 As shown, the process of obtaining the flatness of the local areas of the multiple steel plate surfaces based on the point cloud of the local areas and the standard plane equation includes:

[0102] S61, obtain the distance from the center point of the laser stripe in the point cloud of the local area on the surface of the plurality of steel plates to the center point of the standard plane equation.

[0103] For example, based on the point cloud of a local area on the steel plate surface and the standard plane equation W when there is no steel plate coverage, the distances from the center points of all laser stripes in the three-dimensional point cloud of each small facet of the steel plate to the standard plane W can be obtained. Wherein, the distance d is the center point distance of each laser stripe in each region. i It can be represented as:

[0104]

[0105] S62, obtain the flatness of local areas on the surfaces of the plurality of steel plates based on the distance between the center points.

[0106] For example, the flatness E of a local area on the surface of each steel plate is represented as:

[0107]

[0108] In one embodiment of this application, the steel plate flatness detection method further includes: comparing the flatness of multiple local areas on the surface of the steel plate with a flatness threshold, and obtaining the flatness state of the steel plate surface based on the comparison result.

[0109] For example, the actual flatness of a local area on the surface of each steel plate is compared with the flatness threshold E0. When the actual flatness value is less than the flatness threshold E0, the local area on the surface of the steel plate is determined to be concave; when the actual flatness value is greater than the flatness threshold E0, the local area on the surface of the steel plate is determined to be convex.

[0110] It should be noted that the flatness threshold can be adjusted according to the actual condition of the steel plate in the scenario.

[0111] The following will provide a detailed description of the steel plate flatness detection method provided in this application through a specific example. It should be noted that the content of this example is only used to explain and illustrate the steel plate flatness detection method provided in this application, and is not intended to limit the scope of protection of this application in any way. In specific applications, corresponding steps can be added or deleted based on this example according to actual needs. The steps of the steel plate flatness detection method include:

[0112] Step 1: Preparatory operations for steel plate surface inspection. First, laser stripe projection is performed to obtain reference surface data. It is then determined whether the steel plate is within the non-overlapping camera's field of view. If the steel plate is within the camera's non-overlapping field of view, flatness standards are set, laser stripe projection is performed, and the steel plate is segmented and positioned. If the steel plate is not within the camera's non-overlapping field of view, the process waits for the steel plate to enter the camera's field of view.

[0113] Step two: Acquire local images of the steel plate surface from each camera's perspective. Laser calibration is performed on the steel plate surface, structured light fringes are projected, and each industrial camera acquires a local image of the steel plate surface from its respective perspective.

[0114] Step 3: Process the local image of the steel plate surface. Perform sub-pixel edge detection and noise reduction on the local image of the steel plate surface, and extract the ROI region of the continuous casting slab cross-section. Then, extract the center point of the laser stripe structured light in the preprocessed local area to obtain the 3D point cloud of the steel plate surface. Use a stripe centerline extraction algorithm to extract the center of the structured light stripes from the preprocessed steel plate surface image. Obtain the normal direction of the stripes using the Hessian matrix, and then apply a Taylor polynomial expansion to the pixel grayscale along the normal direction to obtain the grayscale distribution function, thereby obtaining the sub-pixel position of the stripe center. Based on the camera parameters obtained from camera calibration, calculate the closed-form solution of the object point coordinates to extract the 3D coordinate information of all points on the centerline of the stripes on the steel plate surface. Finally, using the relative pose relationship between the four cameras with non-overlapping fields of view, stitch the 3D coordinate information of the centerline of the stripes on the steel plate surface from the four cameras onto the entire steel plate plane.

[0115] Step four: Fit the standard plane to the 3D point cloud of the steel plate surface to obtain the flatness value and flatness status of each local area on the steel plate surface. Obtain the standard plane equation by least squares fitting based on the reconstructed 3D point cloud of the steel plate surface and the standard steel plate reference plane. Based on the standard plane equation, obtain the distance from the spatial coordinates of the light stripe centerline region of each 1m*1m local area of ​​the steel plate to the standard plane equation, and further obtain the actual flatness value of each small area. Compare the actual flatness value with the flatness threshold to finally obtain the flatness information of each area in each small area after the steel plate is divided. Reconstruct the actual 3D point cloud of the fitted steel plate surface using image processing algorithms and display it in the "3D Point Cloud Display" on the display interface, such as... Figure 15 As shown, the real-time flatness results of each area in the divided small regions of the steel plate are obtained based on the flatness detection from the actual 3D point cloud of the steel plate surface to the standard plane, and are displayed in the "Flatness Measurement Results" interface, such as... Figure 16 As shown.

[0116] In summary, the steel plate flatness detection method provided in this application utilizes a laser emitter to project laser stripes onto the steel plate surface and employs multiple industrial cameras to construct a non-overlapping field of view. Local image acquisition and preprocessing are performed on each camera's viewpoint area. The acquired laser stripe center lines are then used to further obtain a 3D point cloud of the local area of ​​the steel plate. A standard plane equation is then fitted, and the flatness value of each local area on the steel plate surface is obtained by measuring the distance from the laser stripe center point to the standard plane. The actual flatness value is compared with a set flatness threshold to determine the flatness of the local area on the steel plate surface. This steel plate flatness detection method can automatically complete the flatness detection of the steel plate surface, improving work efficiency and reducing labor costs. By utilizing laser stripe surface partitioning and stripe center line extraction technology, high-precision flatness detection of the steel plate surface is achieved. The detection results are visualized in the form of 3D point clouds and charts, facilitating user understanding. This steel plate flatness detection method achieves automatic, high-precision, and visualized flatness detection of steel plate surfaces, effectively improving the quality control level of steel plates.

[0117] The scope of protection for the steel plate flatness detection method described in this application is not limited to the order of steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0118] This application also provides a steel plate flatness detection system, which can implement the steel plate flatness detection method described in this application. However, the implementation device of the steel plate flatness detection method described in this application includes, but is not limited to, the structure of the steel plate flatness detection system listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0119] Figure 17 The diagram shown is a structural schematic of a steel plate flatness detection system according to one embodiment of this application. Figure 17 As shown, the steel plate flatness detection system 1 includes: a preparation module 11, an image acquisition module 12, an image processing module 13, and a flatness acquisition module 14. The preparation module 11 is used to construct a non-overlapping field of view using multiple industrial cameras and to project laser stripes using a laser emitter. The image acquisition module 12 is used to acquire images of the steel plate surface covering the laser stripes to obtain local images of the steel plate surface within the viewing areas of each of the industrial cameras. The image processing module 13 is used to process the local images of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface. The flatness acquisition module 14 is used to obtain the flatness of multiple local areas of the steel plate surface based on the three-dimensional point cloud of the steel plate surface.

[0120] It should be noted that, Figure 17 The modules in the steel plate flatness detection system 1 shown are related to... Figure 4 The steps in the steel plate flatness detection method are all corresponding and will not be repeated here.

[0121] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0122] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0123] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] This application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, this computer program implements the steel plate flatness detection method provided in this application. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The above storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0125] This application embodiment may also provide an electronic device. Figure 18 The diagram shown is a structural schematic of an electronic device 2 according to an embodiment of this application. Figure 18 As shown, in this embodiment, the electronic device 2 includes a memory 21 and a processor 22.

[0126] The memory 21 is used to store computer programs. In some possible implementations, the memory 21 may include various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0127] In this embodiment, memory 21 may include a computer system readable medium in the form of volatile memory, such as RAM and / or cache memory. Electronic device 2 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 21 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0128] The processor 22 is connected to the memory 21 and is used to execute the computer program stored in the memory 21 so that the electronic device 2 performs the steel plate flatness detection method.

[0129] For example, processor 22 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. In other embodiments, processor 22 may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0130] In some implementations, the electronic device 2 provided in this application embodiment may further include a display 23. The display 23 is communicatively connected to the memory 21 and the processor 22, and is used to display a graphical user interface (GUI) related to the steel plate flatness detection method.

[0131] In this embodiment, the display 23 may include a display screen (display panel). In some implementations, the display panel may be configured using a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Alternatively, the display 23 may also be a touch panel (touchscreen, touch screen), which may include a display screen and a touch-sensitive surface. When the touch-sensitive surface detects a touch operation on or near it, it transmits the information to the processor 22 to determine the type of touch event. Subsequently, the processor 22 provides corresponding visual output on the display device based on the type of touch event.

[0132] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0133] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for detecting the flatness of steel plates, characterized in that, The method for detecting the flatness of steel plates includes: Multiple industrial cameras are used to construct a non-overlapping field of view, and laser stripes are projected using a laser emitter. Image acquisition is performed on the surface of the steel plate covered with laser stripes to obtain local images of the steel plate surface in the field of view of each of the industrial cameras; The local image of the steel plate surface is processed to obtain a three-dimensional point cloud of the steel plate surface; The flatness of multiple local areas on the surface of the steel plate is obtained based on the three-dimensional point cloud of the steel plate surface.

2. The method for detecting the flatness of steel plates according to claim 1, characterized in that, The process of processing a local image of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface includes: The local image of the steel plate surface is preprocessed to obtain a preprocessed local image of the steel plate surface; Laser stripe center lines are extracted from the preprocessed local images of the steel plate surface to obtain laser center point clouds in the field of view of each industrial camera. The laser center point cloud of each of the industrial camera's field of view is stitched together to obtain a three-dimensional point cloud on the surface of the steel plate.

3. The method for detecting the flatness of steel plates according to claim 2, characterized in that, The process of obtaining the laser center point cloud of the field of view of each of the aforementioned industrial cameras also includes: Single-target positioning is performed on the industrial cameras to obtain the internal parameters of each industrial camera; Multi-target positioning is performed on the industrial cameras to obtain the relative attitudes between the multiple industrial cameras; Based on the internal parameters and the relative attitude, coordinate transformation is performed on the laser line center point of each industrial camera's field of view to obtain the laser center point cloud of each industrial camera's field of view.

4. The method for detecting the flatness of steel plates according to claim 2, characterized in that, The process of obtaining the flatness of multiple local areas on the surface of the steel plate based on the three-dimensional point cloud of the steel plate surface includes: The standard plane equation of the steel plate reference surface is obtained by fitting and updating the coordinate points in the laser center point cloud. The three-dimensional point cloud on the surface of the steel plate is partitioned to obtain multiple local point clouds on the surface of the steel plate. The flatness of the local areas on the surface of the multiple steel plates is obtained based on the point cloud of the local areas and the standard plane equation.

5. The method for detecting the flatness of steel plates according to claim 4, characterized in that, The process of fitting and updating the coordinates of the laser center point cloud to obtain the standard plane equation of the steel plate reference surface includes: Obtain a first coordinate point, a second coordinate point, and a third coordinate point, wherein the first coordinate point, the second coordinate point, and the third coordinate point are three points in the laser center point point cloud that are not on the same straight line; Fit the first coordinate point, the second coordinate point, and the third coordinate point to a reference plane equation; The reference plane equation is updated and corrected using the remaining coordinate points in the laser center point cloud to obtain the standard plane equation.

6. The method for detecting the flatness of steel plates according to claim 4, characterized in that, The process of obtaining the flatness of the local areas of the multiple steel plate surfaces based on the point cloud of the local areas and the standard plane equation includes: Obtain the distance from the center point of the laser stripe in the point cloud of the local area on the surface of the multiple steel plates to the center point of the standard plane equation; The flatness of local areas on the surfaces of the plurality of steel plates is obtained based on the distance between the center points.

7. The method for detecting the flatness of steel plates according to claim 1, characterized in that, The steel plate flatness detection method further includes: comparing the flatness of multiple local areas on the surface of the steel plate with a flatness threshold, and obtaining the flatness state of the steel plate surface based on the comparison results.

8. A steel plate flatness detection system, characterized in that, The steel plate flatness detection system includes: The preparation module is used to construct a non-overlapping field of view using multiple industrial cameras and to project laser stripes using a laser emitter. The image acquisition module is used to acquire images of the steel plate surface covered with laser stripes in order to obtain local images of the steel plate surface in the field of view area of ​​each of the industrial cameras; An image processing module is used to process a local image of the steel plate surface to obtain a three-dimensional point cloud of the steel plate surface; The flatness acquisition module is used to acquire the flatness of multiple local areas on the surface of the steel plate based on the three-dimensional point cloud of the steel plate surface.

9. An electronic device, characterized in that, The electronic device includes: A memory on which computer programs are stored; A processor, communicatively connected to the memory, is used to execute the computer program to implement the steel plate flatness detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by an electronic device, the program implements the steel plate flatness detection method as described in any one of claims 1 to 7.

Images