Detection method and detection system for strip steel cutting

Abstract

The invention provides a strip steel cutting detection method and system, and belongs to the field of steel machining and manufacturing. The strip steel cutting detection method provided by the invention comprises the following steps: obtaining strip steel image data and transportation area contour data; carrying out contour segmentation processing on the transportation area contour data along the length direction to obtain scanning grid set data comprising a first grid, and respectively obtaining length values of the first grid along the width direction and the length direction; fitting the strip steel image data and the scanning grid set data to obtain intersection section contour features of the strip steel and the transportation area; and determining the actual width of the strip steel and the actual distance between the strip head and / or the strip tail of the strip steel and the cutter based on the contour features of the intersection section and the length values of the first grids in the width direction and the length direction. By means of the strip steel cutting detection method, the accuracy and analysis efficiency of strip steel width analysis and strip steel-to-cutter distance analysis can be improved, and the strip steel cutting efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of steel processing and manufacturing, and particularly relates to a detection method and detection system for strip steel cutting. Background Art

[0002] Strip steel is a strip-shaped metal material, usually processed from a steel billet through a continuous rolling process, with a certain width and thickness. Strip steel cutting, as a key process for producing steel segments from strip steel, has an important impact on the production quality and packaging efficiency of steel segments.

[0003] Strip steel is usually cut and processed by a shearing device equipped with a transportation mechanism (such as a conveyor belt). Divided along the length direction, strip steel can be successively divided into three major components: a strip tail, a main body, and a strip head. When cutting strip steel, it is necessary to determine the cutting point of the cutting tool on the strip steel on the conveyor belt. Due to the different shapes of the strip head (including various shapes such as trapezoidal, semi-circular arc, and triangular), the width at each part of the strip head is usually uneven. Therefore, it is necessary to calculate the width distribution of the strip steel position to determine the optimal cutting point to ensure that the widths of all parts of the steel segment are equal. In the prior art, manual analysis of the strip steel width and the distance between the strip steel and the cutting tool is usually adopted. However, the accuracy and efficiency of manual analysis are low, and there are safety risks, which seriously restrict the improvement of strip steel cutting efficiency.

[0004] In view of the above, the present invention is specifically proposed. Summary of the Invention

[0005] This application provides a detection method and detection system for strip steel cutting to solve the technical problems of low accuracy and efficiency, and safety risks caused by manually analyzing the strip steel width and the distance between the strip steel and the cutting tool in the prior art.

[0006] The first aspect of this application provides a detection method for strip steel cutting, which is used to detect the width of strip steel and the distance between the strip steel and the cutting tool, and includes the following steps:

[0007] Based on the strip steel in the transportation area, strip steel image data and transportation area contour data are respectively obtained;

[0008] The transportation area contour data is processed by contour segmentation along the length direction to obtain a scanned grid set data including a plurality of first grids, and the length values of each first grid along the width direction and along the length direction are respectively obtained;

[0009] The strip steel image data and the scanned grid set data are fitted to obtain the contour features of each intersection segment between the strip steel and the transportation area;

[0010] Based on each intersection segment contour feature and the length value of each first grid along the width direction, the actual width of the strip steel is determined;

[0011] Based on the contour features of each intersection segment and the length values of each first grid along the length direction, determine the actual distance between the leading end and / or the trailing end of the strip steel and the cutting tool.

[0012] In some embodiments, fitting the strip steel image data and the scanned grid set data to obtain the contour features of each intersection segment between the strip steel and the transportation area, including:

[0013] Perform segmented mask extraction processing on the strip steel image data along the length direction to obtain strip steel mask segmented data including a plurality of second grids;

[0014] Traverse the intersection contours of each first grid and each second grid to obtain the contour features of each intersection segment.

[0015] In some embodiments, the detection method further includes:

[0016] Based on the strip steel mask segmented data, when it is detected that the distance between the strip steel and the entrance and / or the exit of the transportation area along the length direction is zero, it is determined that the leading end and / or the trailing end of the strip steel is not detected; and / or

[0017] Based on the strip steel mask segmented data, when it is detected that the distance between the strip steel and the entrance and / or the exit of the transportation area along the length direction is less than zero, it is determined that the leading end and / or the trailing end of the strip steel is detected.

[0018] In some embodiments, perform contour segmentation processing on the transportation area contour data along the length direction to obtain a scanned grid set data including a plurality of first grids, and respectively obtain the length values of each first grid along the width direction and along the length direction, including:

[0019] Perform regional segmentation on the transportation area contour data along the length direction to obtain a plurality of first grids arranged along the length direction;

[0020] Perform perspective transformation processing on the plurality of first grids arranged along the length direction to obtain a scanned grid set data including a plurality of first grids that satisfies the perspective relationship;

[0021] Obtain the actual width of the cutting tool, and perform proportional transformation on the scanned grid set data that satisfies the perspective relationship in combination with the actual width of the cutting tool to respectively obtain the length values of each first grid along the width direction and along the length direction.

[0022] In some embodiments, perform segmented mask extraction processing on the strip steel mask data along the length direction to obtain strip steel mask segmented data including a plurality of second grids, including:

[0023] Based on a preset algorithm model, perform feature extraction processing on the strip steel image data to obtain first mask data;

[0024] Perform hole filling on the first mask data and extract the largest connected component to obtain the second mask data;

[0025] Perform feature optimization on the second mask data and perform segmentation processing along the length direction to obtain strip mask segmentation data including a plurality of second grids.

[0026] In some embodiments, determining the actual width of the strip based on the contour feature of each intersection segment and the length value of each first grid in the width direction includes:

[0027] Divide the strip into a strip body, a strip head, and / or a strip tail based on the width increasing inflection point of the contour feature of each intersection segment to obtain strip body contour data, strip head contour data, and / or strip tail contour data;

[0028] Extract the length value of each second grid in the width direction in the strip body contour data, strip head contour data, and / or strip tail contour data;

[0029] Based on the length value of each first grid in the width direction, perform proportional transformation on the length value of each extracted second grid in the width direction to determine the actual width of the strip.

[0030] In some embodiments, determining the actual distance between the strip head and / or strip tail and the cutter based on the contour feature of each intersection segment and the length value of each first grid in the length direction includes:

[0031] In the case where it is determined that the strip head and / or strip tail is detected, divide the strip into a strip body, a strip head, and / or a strip tail based on the width increasing inflection point of the contour feature of each intersection segment, and obtain strip head contour data and / or strip tail contour data;

[0032] Based on the strip head contour data and / or strip tail contour data, extract the length value of each second grid in the length direction in the strip head contour data and / or strip tail contour data;

[0033] Based on the length value of each first grid in the length direction, perform proportional transformation on the length value of each extracted second grid in the length direction to determine the actual width of the strip head and / or strip tail and the actual distance between the strip head and / or strip tail and the cutter.

[0034] In some embodiments, extracting the length value of each second grid in the length direction in the strip head contour data and / or strip tail contour data based on the strip head contour data and / or strip tail contour data includes;

[0035] Perform reverse gradient filtering processing on the strip head contour data and / or strip tail contour data, and extract the length value of each second grid in the length direction in the strip head contour data and / or strip tail contour data after the reverse gradient filtering processing.

[0036] In some embodiments, the actual width of the strip includes the average width of the strip, the minimum width of the strip, and the maximum width of the strip.

[0037] The second aspect of the present application provides a detection system for strip cutting, which is used to apply the detection method for strip cutting as described above, and includes: at least two image acquisition modules, which are used to respectively acquire strip image data and transportation area contour data based on the strip in the transportation area; a control module, electrically connected to the image acquisition module, and is used to control the image acquisition module to acquire strip image data and transportation area contour data; a processing module, electrically connected to the control module and the image acquisition module, and is used to be controlled by the control module to process the transportation area contour data and strip image data to respectively determine the actual width of the strip and / or determine the actual distance between the leading end and / or trailing end of the strip and the cutting tool; an image display module, electrically connected to the control module, and is used to perform real-time image display on the transportation area contour data and strip image data.

[0038] According to the third aspect of the present application, there is provided an electronic device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the detection method for strip cutting as described above is implemented.

[0039] According to the fourth aspect of the present application, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the detection method for strip cutting as described above is implemented.

[0040] In summary, the detection method and detection system for strip cutting provided by the present application at least have the following beneficial effects:

[0041] The strip cutting detection method provided by this application includes: based on the strip within the transportation area, obtaining strip image data and transportation area contour data respectively. By obtaining the strip image data and transportation area contour data for the transportation area and the strip within the transportation area respectively, the process of automatically obtaining the shape and position information of the strip is realized, thus avoiding traditional manual measurement and analysis, and further improving efficiency and reducing human error; further performing contour segmentation processing on the transportation area contour data along the length direction to obtain a scanned grid set data including multiple first grids. The scanned grid set data including multiple first grids can be used to fit with the strip image data to further determine the actual shapes and positions of each part such as the strip tail, strip head, and strip body, providing data support for subsequent strip width analysis and distance analysis from the cutting tool; by obtaining the length values of each first grid along the width direction and along the length direction respectively, these length values can be used for subsequent strip width analysis and determination of the distance from the cutting tool; by fitting the strip image data and the scanned grid set data, the contour features of each intersection segment between the strip and the transportation area are obtained. Each obtained intersection segment contour feature can more accurately obtain the actual shape and position of the strip, especially for the actual shapes and positions of parts with complex shapes such as the strip head and / or strip tail, to improve the accuracy during subsequent width analysis; further, based on each intersection segment contour feature and the length value of each first grid along the width direction, the actual width of the strip and the overall width information of the strip can be determined, ensuring the uniformity and accuracy during the strip cutting process, improving the cutting quality and processing efficiency; and in the case of detecting the strip head or strip tail, based on each intersection segment contour feature and the length value of each first grid along the length direction, the actual distances between the strip head and / or strip tail and the cutting tool can also be determined, which is beneficial for determining the optimal cutting point position, thus realizing an equal-width cutting effect at each position of the strip and improving the cutting quality and production efficiency.

[0042] Thus, by dividing the transportation area into a scanned grid set data including multiple first grids along the length direction in this application, and obtaining the contour features of the intersection segments when the strip image data passes through the first grid, further combining the length values of the first grid in the length direction and the width direction, the actual width of the strip on the transportation area and the actual distance from the cutting tool are accurately determined, greatly improving the accuracy of strip width detection analysis and distance detection analysis from the cutting tool. While improving the detection efficiency, the safety risks brought by manual analysis are avoided, and thus the strip cutting efficiency is significantly promoted.

[0043] Other advantages and features of the strip cutting detection method and detection system provided by this application will be further elaborated in the subsequent specific embodiments. Brief Description of the Drawings

[0044] To more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0046] Figure 2 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0047] Figure 3 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0048] Figure 4 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0049] Figure 5 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0050] Figure 6 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0051] Figure 7 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0052] Figure 8 Flowchart of a strip cutting detection method provided by an embodiment of the present application;

[0053] Figure 9 Structural diagram of a strip cutting detection system provided by an embodiment of the present application;

[0054] Figure 10 Structural diagram of an electronic device provided by an embodiment of the present application;

[0055] Figure 11 On-site schematic diagram during strip cutting detection provided by an embodiment of the present application;

[0056] Figure 12 On-site schematic diagram during strip cutting detection provided by an embodiment of the present application;

[0057] Figure 13 On-site schematic diagram during strip cutting detection provided by an embodiment of the present application;

[0058] Figure 14 Schematic diagram of the on-site inspection during strip steel cutting provided for the embodiments of the present application;

[0059] Figure 15 Schematic diagram of the on-site inspection during strip steel cutting provided for the embodiments of the present application. Detailed implementation manners

[0060] To make the above and other features and advantages of the present application clearer, the present application will be further described below with reference to the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are merely exemplary, not restrictive.

[0061] In the following description, many specific details are set forth to provide a thorough understanding of the present application. However, it is obvious to those skilled in the art that the present application does not need to adopt specific details to be practiced. In other cases, well-known steps or operations are not described in detail to avoid obscuring the present application.

[0062] The strip steel cutting detection method provided by the embodiments of the present application can be executed by the strip steel cutting detection system 10 provided by the embodiments of the present application, and this system can be configured in the electronic device 400.

[0063] As mentioned above, the general inventive concept of the present application is to provide a strip steel cutting detection method. By designing the detection method, when the strip steel is transported and sheared in the shearing device, strip steel image data is collected for the strip steel, and transportation area contour data is collected for the transportation area. Further, after the transportation area contour data is subjected to contour segmentation processing along the length direction, a scanned grid set data including a plurality of first grids can be obtained. By fitting the strip steel image data with the scanned grid set data and extracting the intersection, the contour features of each intersection segment between the strip steel and the transportation area can be obtained, and based on the length value of each first grid in the length direction and the length value in the width direction, the actual width of the strip steel can be determined, and the actual distance between the leading end and / or the trailing end of the strip steel and the cutting tool can be determined. Thus, the automation of strip steel width detection is achieved, and the detection accuracy and detection efficiency of the strip steel width and the distance between the strip steel and the cutting tool are greatly improved, the safety risks brought by manual analysis are avoided, and the improvement of strip steel cutting efficiency is effectively promoted.

[0064] It should be noted that in the embodiments of the present application, the length direction refers to the transportation direction of the strip steel, and the width direction refers to the direction perpendicular to the length direction in the same horizontal plane.

[0065] Based on the above general concept, referring to Figures 1 to 8 , the embodiments of the present application first provide a strip steel cutting detection method for detecting the width of the strip steel and the distance between the strip steel and the cutting tool, including the following steps:

[0066] S100. Based on the strip steel within the transportation area, respectively obtain strip steel image data and transportation area contour data;

[0067] S200. Perform contour segmentation processing on the transportation area contour data along the length direction to obtain a scanned grid set data including a plurality of first grids, and respectively obtain the length values of each first grid along the width direction and along the length direction;

[0068] S300. Fit the strip steel image data and the scanned grid set data to obtain the contour features of each intersection segment between the strip steel and the transportation area;

[0069] S400. Based on the contour features of each intersection segment and the length values of each first grid along the width direction, determine the actual width of the strip steel;

[0070] S500. Based on the contour features of each intersection segment and the length values of each first grid along the length direction, determine the actual distance between the leading end and / or the trailing end of the strip steel and the cutting tool.

[0071] It should be noted that the transportation area in this embodiment may be the planar area of the transportation mechanism in the shearing device for supporting the strip steel and driving the strip steel for transportation to perform shearing. For example, the transportation area may be the top surface area of the conveyor belt in the shearing device.

[0072] In addition, in the application scenario of the strip steel cutting detection method provided in this embodiment, the shearing device includes a conveyor belt and a cutting tool. The top of the conveyor belt is calibrated as the transportation area, and a cutting tool is arranged in the top space at one end of the conveyor belt to shear the strip steel through the cutting tool when the conveyor belt conveys the strip steel to the bottom of the cutting tool.

[0073] In step S100 of this embodiment, the strip steel is located on the transportation area. Based on the strip steel within the transportation area, respectively obtain strip steel image data and transportation area contour data. At least two image acquisition modules can be used to respectively extract images of the strip steel and the transportation area to respectively obtain strip steel image data and transportation area contour data. By respectively obtaining the strip steel image data and the transportation area contour data, preliminary strip steel shape and position information can be obtained to facilitate subsequent analysis.

[0074] In step S200, perform contour segmentation processing on the transportation area contour data along the length direction to obtain Figures 13 to 15The scanned grid set data (blue grids) including multiple first grids are shown, and the length values of each first grid in the width direction and the length direction are respectively obtained; it should be understood that by performing contour segmentation processing on the contour data of the transportation area in the length direction, among the scanned grid set data, multiple first grids visually appear in a square shape, and the multiple first grids are arranged adjacent to each other in sequence in the length direction to form the scanned grid set data. By respectively obtaining the length values of each first grid in the width direction and the length direction, after fitting the contour features of each intersection segment between the strip steel and the transportation area in the subsequent process, the actual width of the strip steel and the actual distance between the strip steel and the cutting tool can be calculated and analyzed in combination with the contour features of each intersection segment.

[0075] In step S300, the strip steel image data and the scanned grid set data are fitted to obtain the contour features of each intersection segment between the strip steel and the transportation area; since the strip steel is within the transportation area, by fitting the strip steel image data and the scanned grid set data, the contour features of the intersection segments between the strip steel image data and the multiple first grids can be determined, thereby further determining the actual shape and position of the strip steel, so as to facilitate determining the main body of the strip steel, as well as the leading end and the trailing end.

[0076] In step S400, based on the contour features of each intersection segment and the length value of each first grid in the width direction, the actual width of the strip steel is determined; according to the width distribution of these intersection segment contour features and in combination with the length value of each first grid in the width direction, the actual width value of the strip steel can be further obtained.

[0077] In step S500, based on the contour features of each intersection segment and the length value of each first grid in the length direction, the actual distance between the leading end and / or the trailing end of the strip steel and the cutting tool is determined; according to the width distribution of these intersection segment contour features, it can be further determined whether the current strip steel has a leading end and / or a trailing end. If it is determined that the strip steel has a leading end and / or a trailing end, the actual distance between the leading end and / or the trailing end of the strip steel and the cutting tool can be determined by performing proportional conversion with the length value of each first grid in the length direction for each intersection segment contour feature.

[0078] It should be noted that the width of the strip steel in this application refers to the distance value between the left and right sides of the strip steel in the width direction, and the distance from the cutting tool refers to the distance value between the end of the leading end and / or the trailing end of the strip steel in the length direction and the cutting tool.

[0079] Thus, in this embodiment, the transportation area is divided in the length direction into a set of scan grid data including a plurality of first grids, and by obtaining the contour features of the intersection segments when the strip image data passes through the first grid, further combining the length values of the first grid in the length direction and the width direction, the actual width of the strip on the transportation area and the actual distance from the cutting knife are accurately determined, greatly improving the accuracy of strip width detection and analysis and the detection and analysis of the distance from the cutting knife, improving the detection efficiency while avoiding the safety risks brought by manual analysis, and thus significantly promoting the strip cutting efficiency.

[0080] In some embodiments, in step S300, fitting the strip image data and the set of scan grid data to obtain the contour features of each intersection segment between the strip and the transportation area includes:

[0081] S310. Perform segmented mask extraction processing on the strip image data in the length direction to obtain strip mask segmented data including a plurality of second grids;

[0082] S320. Traverse the intersection contours of each first grid and each second grid to obtain the contour features of each intersection segment.

[0083] It should be understood that due to the irregular shapes of each section of the strip and possible deformations such as waviness or slight arching on the surface, these factors will affect the accuracy of strip width detection and the detection of the distance from the cutting knife, resulting in detection errors.

[0084] Therefore, in this embodiment, through step S310, segmented mask extraction processing is performed on the strip image data in the length direction to obtain strip mask segmented data including a plurality of second grids. Performing segmented mask extraction processing on the strip image data can better capture the shapes and changes of each part of the strip and provide a more accurate data basis for subsequent intersection contour extraction to overcome factors such as the irregular shape of the strip and surface deformations, so as to improve the detection accuracy; further traverse the intersection contours of each first grid and each second grid to obtain the contour features of each intersection segment. By traversing the intersection contours, the shape, length, position, etc. information of each intersection segment can be obtained, so as to accurately calculate the width of the strip and the distance from the cutting knife.

[0085] In some embodiments, step S310, performing segmented mask extraction processing on the strip mask data in the length direction to obtain strip mask segmented data including a plurality of second grids includes:

[0086] S311. Perform feature extraction processing on the strip image data based on a preset algorithm model to obtain first mask data;

[0087] S312. Perform hole filling on the first mask data and extract the largest connected component to obtain the second mask data;

[0088] S313. Optimize the features of the second mask data and perform segmentation processing along the length direction to obtain strip mask segmented data including multiple second grids.

[0089] To further eliminate detection errors caused by factors such as the irregular shape of the strip and surface deformation, in step S311 of this embodiment, based on a preset algorithm model, feature processing is performed on the strip image data to obtain the first mask data. For example, the preset algorithm model in this embodiment can use the EfficientNetV3 model as the neural network backbone, extract the semantic information of each pixel point in the strip image through deep learning, and classify each pixel point as the foreground or background belonging to the strip area through semantic segmentation technology to obtain the first mask data of the strip.

[0090] It can be understood that the EfficientNetV3 model, as a convolutional neural network model, combines multiple optimization strategies, including automatic model scaling, depth and width variability, etc., to provide better performance and efficiency. When using the EfficientNetV3 model for strip feature extraction, a pre-trained EfficientNetV3 model can be used as the backbone of the neural network, and then fine-tuned or further trained according to task requirements. By inputting strip image data, the EfficientNetV3 model can learn different levels of feature representations, including low-level edge and texture features and high-level semantic information. The first mask data obtained after being processed by the EfficientNetV3 model can be a binary image, as Figure 11 and Figure 12 shown, where the strip area is marked as the foreground (red), and other areas are marked as the background (transparent color). Such mask data can better represent the position and shape of the strip and provide an accurate data basis for subsequent processing steps.

[0091] Step S312 obtains the second mask data by performing hole filling on the first mask data and extracting the largest connected component. It should be understood that the hole filling in this embodiment is an image processing method that can fill the holes in the mask to make the mask more complete. Specifically, it can be achieved through a dilation operation, that is, using a structuring element to perform a dilation operation on the mask to fill the hole part. After obtaining the mask data after hole filling, connected component analysis can be used to extract the largest connected component, that is, the area of the strip steel. Connected component analysis can mark each pixel point of the connected component and extract the largest connected component according to the marking information of the pixel points. Thus, the second mask data obtained is a binary mask that only retains the strip steel area, thereby further reducing errors and better extracting the effective information of the strip steel.

[0092] Step S313 obtains the segmented strip steel mask data including multiple second grids by performing feature optimization on the second mask data and segmenting it along the length direction, where the multiple second grids are arranged adjacent to each other in sequence along the length direction; the feature optimization in this embodiment includes finding the convex hull, filling and smoothing the boundary, and boundary correction. Specifically, the convex hull refers to the smallest convex polygon that can enclose a given set of points. In this embodiment, a convex hull algorithm can be used to calculate the convex hull of the second mask data. The convex hull algorithm can determine the boundary points of the convex polygon by sorting and scanning the given set of points. After obtaining the convex hull of the second mask data, image processing methods can be used to fill and smooth the convex hull boundary, such as using an interpolation algorithm or a curve fitting algorithm to generate a smooth boundary line. There may be a certain deviation between the filled and smoothed boundary and the original second mask data. Therefore, in this embodiment, boundary correction can be performed to align the smoothed boundary with the original second mask data to ensure the accuracy and consistency of the boundary.

[0093] After completing the feature optimization, the second mask data is segmented along the length direction to obtain the segmented strip steel mask data including multiple second grids. The segmentation process can divide the strip steel mask into several segments, and each segment corresponds to the strip steel area of a second grid, so as to facilitate subsequent determination of the leading end and / or trailing end of the strip steel, and fitting with the scanning grid set data to obtain the contour feature of each intersection segment between the strip steel and the transportation area. Thus, the obtained segmented strip steel mask data can greatly eliminate the detection errors caused by factors such as the irregular shape of the strip steel and the deformation of the surface, and improve the accuracy of strip steel width detection and the detection of the distance from the cutting tool.

[0094] It should be clear that both the second grid and the first grid are in a square shape, and both the second grid and the first grid include a length side and a width side, and the length sides of the second grid and the first grid have the same direction (width direction), and the width sides have the same direction (length direction), so as to facilitate subsequent fitting and extraction of the intersection contour data.

[0095] In some embodiments, in step S200, the contour data of the transportation area is segmented along the length direction to obtain a set of scanned grid data including a plurality of first grids. Obtaining the length values of each first grid along the width direction and the length direction respectively includes:

[0096] S210. Segment the contour data of the transportation area along the length direction to obtain a plurality of first grids arranged along the length direction;

[0097] S220. Perform a perspective transformation on the plurality of first grids arranged along the length direction to obtain a set of scanned grid data including a plurality of first grids that satisfy the perspective relationship;

[0098] S230. Obtain the actual width of the cutting tool, and perform an equal-scale transformation on the set of scanned grid data that satisfies the perspective relationship in combination with the actual width of the cutting tool to obtain the length values of each first grid along the width direction and the length direction respectively.

[0099] In this embodiment, in step S210, a plurality of first grids arranged along the length direction are obtained by segmenting the contour data of the transportation area along the length direction; in step S220, by performing a perspective transformation on the plurality of first grids arranged along the length direction, the original contour data of the transportation area can be perspective-corrected to make it satisfy the perspective relationship. In this way, a set of scanned grid data including a plurality of first grids that satisfy the perspective relationship is obtained, enabling the set of scanned grid data to better reflect the geometric and spatial relationships in the real world and providing a more accurate basis for subsequent processing; in step S230, by obtaining the actual width of the cutting tool and performing an equal-scale transformation on the set of scanned grid data that satisfies the perspective relationship in combination with the actual width of the cutting tool, the length values of each first grid along the width direction and the length direction obtained can more accurately conform to the actual situation, so as to improve the accuracy of strip width detection and its distance from the cutting tool.

[0100] It should be clear that in this embodiment, the cutting tool is installed on a roller arranged along the width direction, and the actual width of the cutting tool can be obtained by acquiring the end point distances at both ends of the roller.

[0101] In some embodiments, to determine whether the strip on the transportation area has a leading end and / or a trailing end, the detection method further includes:

[0102] S600. Based on the strip mask segmentation data, when it is detected that the distance between the strip and the entrance and / or the exit of the transportation area along the length direction is zero, it is determined that the leading end and / or the trailing end of the strip is not detected; and / or

[0103] S700. Based on the strip mask segmented data, when it is detected that the distance of the strip along the length direction from the entrance and / or the exit of the transportation area is less than zero, it is determined that the leading end and / or the trailing end of the strip is detected.

[0104] In step S600 of this embodiment, based on the strip mask segmented data, by calculating the distance of the strip to the entrance and / or the exit of the transportation area, when it is detected that the distance of the strip along the length direction from the entrance and / or the exit of the transportation area is zero, it indicates that the leading end and / or the trailing end of the strip is not within the transportation area (as Figure 15 shown), and thus it can be determined that the leading end and / or the trailing end of the strip is not detected; correspondingly, in step S600, when it is detected that the distance of the strip along the length direction from the entrance and / or the exit of the transportation area is less than zero, it indicates that the leading end and / or the trailing end of the strip is within the transportation area (as Figure 14 shown), and thus it can be determined that the leading end and / or the trailing end of the strip is detected, so as to facilitate further detection of the distance of the leading end and / or the trailing end from the cutting tool in the length direction, thereby realizing the optimization of the cutting point of the cutting tool.

[0105] In some embodiments, in step S400, determining the actual width of the strip based on the contour feature of each intersection segment and the length value of each first grid in the width direction includes:

[0106] S410. Divide the strip into the strip body, the leading end and / or the trailing end based on the width increasing inflection point of the contour feature of each intersection segment, so as to obtain the strip body contour data, the leading end contour data and / or the trailing end contour data;

[0107] S420. Extract the length value of each second grid in the width direction from the strip body contour data, the leading end contour data and / or the trailing end contour data;

[0108] S430. Based on the length value of each first grid in the width direction, perform an equal ratio transformation on the extracted length value of each second grid in the width direction to determine the actual width of the strip.

[0109] It can be understood that in step S410 of this embodiment, through the width increasing inflection point of the contour feature of each intersection segment, the change of the strip contour can be analyzed to determine different parts of the strip, so as to divide the strip into the leading end, the strip body and the trailing end along the length direction, and then respectively obtain as Figure 13 and Figure 14The strip body contour data (green grid), the strip head contour data, and / or the strip tail contour data (red grid) as shown; in step S420, by further extracting the length values of each second grid in the width direction in the strip body contour data, the strip head contour data, and / or the strip tail contour data, it helps to determine the actual width of the strip in combination with the length value of the first grid in the width direction; in step S430, based on the length values of each first grid in the width direction, an equal-proportion transformation is performed on the length values of the corresponding second grids located on the first grid in the width direction, and the actual widths of each section of the strip can be obtained to respectively determine the average width, the minimum width, and the maximum width of the strip, so as to accurately determine the actual width of the strip and improve the cutting efficiency of the strip.

[0110] It should be clear that the width increasing inflection point in this embodiment refers to the inflection point formed by the width values of multiple second grids along the transportation direction. By identifying the width increasing inflection point, the strip can be divided into the strip body, the strip head, and / or the strip tail, and then the contour data of each section of the strip can be obtained.

[0111] In some embodiments, in step S500, determining the actual distance between the strip head and / or the strip tail and the cutting tool based on the contour features of each intersection segment and the length value of each first grid in the length direction includes:

[0112] S510. In the case where it is determined that the strip head and / or the strip tail is detected, the strip is divided into the strip body, the strip head, and / or the strip tail based on the width increasing inflection point of the contour features of each intersection segment, and the strip head contour data and / or the strip tail contour data are obtained;

[0113] S520. Based on the strip head contour data and / or the strip tail contour data, the length values of each second grid in the length direction in the strip head contour data and / or the strip tail contour data are extracted;

[0114] S530. Based on the length values of each first grid in the length direction, an equal-proportion transformation is performed on the length values of each second grid in the length direction extracted, so as to determine the actual width of the strip head and / or the strip tail and the actual distance between the strip head and / or the strip tail and the cutting tool.

[0115] In this embodiment, the leading end and / or the trailing end of the strip steel can be detected and determined through step S700, and the cutting knife is located at the end of the transportation area (i.e., at the first grid at the very end in the transportation direction). In step S510, when it is determined that the leading end and / or the trailing end of the strip steel is detected, the strip steel is divided into the strip steel body, the leading end, and / or the trailing end based on the width increasing inflection points of the profile features of each intersection segment, and the leading end profile data and / or the trailing end profile data are obtained to facilitate calibrating the ends of the leading end and / or the trailing end, so as to determine the actual distance between the leading end and / or the trailing end and the cutting knife; in step S520, based on the leading end profile data and / or the trailing end profile data, the length values of each second grid along the length direction in the leading end profile data and / or the trailing end profile data are extracted, and these length values represent the dimensions of the second grid in the length direction of the leading end and / or the trailing end. Through step S530, the length values of each second grid along the length direction extracted are proportionally transformed based on the length values of each first grid along the length direction to accurately determine the position and distance of the leading end and / or the trailing end in the actual space, so as to determine the actual width of the leading end and / or the trailing end and the actual distance between the leading end and / or the trailing end and the cutting knife.

[0116] Exemplarily, in a specific embodiment, the actual distance between the end of the leading end and / or the trailing end and the cutting knife is calibrated with a red line in the transportation direction, where the end of the leading end and / or the trailing end and the foot points of the leading end and / or the trailing end to the roller of the cutting edge are calibrated with blue points, and the dimension of the proportional transformation of the red line between the two blue points is the actual distance between the leading end and / or the trailing end and the cutting knife.

[0117] Furthermore, the extraction of the length values of each second grid along the length direction in the leading end profile data and / or the trailing end profile data based on the leading end profile data and / or the trailing end profile data in step S530 includes:

[0118] S531. Perform reverse gradient filtering processing on the leading end profile data and / or the trailing end profile data, and extract the length values of each second grid along the length direction in the leading end profile data and / or the trailing end profile data after the reverse gradient filtering processing.

[0119] In this embodiment, reverse gradient filtering is an image processing technology for detecting edges and contours. By applying reverse gradient filtering, the contour features of the leading end and / or the trailing end area can be enhanced to obtain more accurate and clear leading end and / or trailing end profile data, and the error of the actual width of the leading end and / or the trailing end and the actual distance between the leading end and / or the trailing end and the cutting knife can be reduced.

[0120] In some embodiments, the actual width of the strip steel includes the average width of the strip steel, the minimum width of the strip steel, and the maximum width of the strip steel.

[0121] Reference Figure 9, the embodiment of the present application further provides a detection system 10 for strip cutting, which is used to apply the detection method for strip cutting as described above, and includes: at least two image acquisition modules 20, which are used to respectively obtain strip image data and transportation area contour data based on the strip in the transportation area; a control module 30, electrically connected to the image acquisition module 20, which is used to control the image acquisition module 20 to obtain strip image data and transportation area contour data; a processing module 40, electrically connected to the control module 30 and the image acquisition module 20, which is used to be controlled by the control module 30 to process the transportation area contour data and strip image data to respectively determine the actual width of the strip and / or determine the actual distance between the leading end and / or trailing end of the strip and the cutting tool. Through the design of the detection system 10 for strip cutting in this embodiment, the above detection method can be implemented during strip cutting, thereby improving the detection accuracy and detection efficiency of the strip width and its distance from the cutting tool.

[0122] In some embodiments, the detection system 10 further includes an image display module 50, which is electrically connected to the control module 30 to perform real-time image display of the strip, transportation area, cutting tool, etc., and present the overall contour of the strip, the second grid of each section of the strip, and the first grid of the transportation area with different visual effects, and show the numerical values of the detection results in the image display. Specifically, as Figures 11 to 15 shown, in the figure, the label "DAIWEI" determines the result of whether there is a leading end / trailing end, "MIN" is the minimum width of the trailing end, "MAX" is the maximum width of the trailing end, "AVG" is the average width of the trailing end, and "DIST" is the distance from the trailing end to the cutting edge, so as to facilitate the staff to understand the detection results of strip cutting in real time.

[0123] It should be understood that the specific features, operations, and details described above regarding the method of the present application can also be similarly applied to the device and system of the present application, or vice versa. In addition, each step of the method of the present application described above can be executed by the corresponding components or units of the device or system of the present application.

[0124] It should be understood that each module / unit of the device of the present application can be implemented in whole or in part by software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the processor of the electronic device in the form of hardware or firmware or independent of the processor, or stored in the memory of the electronic device in the form of software for the processor to call to execute the operations of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0125] As Figure 10As shown in the figure, the present application provides an electronic device 400, which includes a processor 401 and a memory 402 storing computer program instructions. Among them, when the processor 401 executes the computer program instructions, each step of the above-described strip cutting detection method is implemented. The electronic device 400 can be broadly a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities.

[0126] In one embodiment, the electronic device 400 may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The processor of the electronic device 400 can be used to provide necessary computing, processing, and / or control capabilities. The memory of the electronic device 400 may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the electronic device 400 can be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, the steps of the method of the present application are executed.

[0127] The present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-described strip cutting detection method is implemented.

[0128] Those skilled in the art can understand that the method steps of the present application can be completed by a computer program instructing relevant hardware such as the electronic device 400 or the processor. The computer program can be stored in a non-transitory computer-readable storage medium, and when the computer program is executed, the steps of the present application are caused to be executed. Depending on the situation, any reference to a memory, storage, or other medium in this article may include non-volatile or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0129] The above-described technical features can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification as long as such a combination does not exist in contradiction.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A detection method for strip steel cutting, characterized in that, for detecting the width of the strip steel and the distance between the strip steel and the cutting tool, comprising the following steps: Based on the strip steel in the transportation area, strip steel image data and transportation area contour data are respectively obtained; Perform contour segmentation processing on the transportation area contour data along the length direction to obtain a scanned grid set data including a plurality of first grids, and respectively obtain the length values of each of the first grids along the width direction and along the length direction; Fit the strip steel image data and the scanned grid set data to obtain the contour features of each intersection segment between the strip steel and the transportation area; Based on each of the intersection segment contour features and the length values of each of the first grids along the width direction, determine the actual width of the strip steel; Based on each of the intersection segment contour features and the length values of each of the first grids along the length direction, determine the actual distance between the leading end and / or the trailing end of the strip steel and the cutting tool.

2. The detection method for strip steel cutting according to claim 1, characterized in that, The fitting of the strip steel image data and the scanned grid set data to obtain the contour features of each intersection segment between the strip steel and the transportation area includes: Perform segmented mask extraction processing on the strip steel image data along the length direction to obtain strip steel mask segmented data including a plurality of second grids; Traverse the intersection contours of each of the first grids and each of the second grids to obtain the contour features of each intersection segment.

3. The detection method for strip steel cutting according to claim 2, characterized in that, further comprising: Based on the strip steel mask segmented data, when it is detected that the distance between the strip steel and the entrance and / or the exit of the transportation area along the length direction is zero, it is determined that the leading end and / or the trailing end of the strip steel is not detected; and / or Based on the strip steel mask segmented data, when it is detected that the distance between the strip steel and the entrance and / or the exit of the transportation area along the length direction is less than zero, it is determined that the leading end and / or the trailing end of the strip steel is detected.

4. The detection method for strip steel cutting according to claim 2, characterized in that, The performing of contour segmentation processing on the transportation area contour data along the length direction to obtain a scanned grid set data including a plurality of first grids, and respectively obtaining the length values of each of the first grids along the width direction and along the length direction includes: Perform regional segmentation on the transportation area contour data along the length direction to obtain a plurality of first grids arranged along the length direction; Perform perspective transformation processing on the plurality of first grids arranged along the length direction to obtain a scanned grid set data including a plurality of first grids that satisfies the perspective relationship; Obtain the actual width of the cutting tool, and perform proportional transformation on the scanned grid set data that satisfies the perspective relationship in combination with the actual width of the cutting tool to respectively obtain the length values of each of the first grids along the width direction and along the length direction.

5. The detection method for strip steel cutting according to claim 2, characterized in that, The performing of segmented mask extraction processing on the strip steel mask data along the length direction to obtain strip steel mask segmented data including a plurality of second grids includes: Performing feature extraction processing on the strip image data based on a preset algorithm model to obtain first mask data; Performing hole filling on the first mask data and extracting the largest connected region to obtain second mask data; Performing feature optimization on the second mask data and segmenting it along the length direction to obtain strip mask segmented data including a plurality of second grids.

6. The strip cutting detection method according to claim 2, wherein, The determining the actual width of the strip based on each of the intersection segment contour features and the length value of each of the first grids in the width direction includes: Dividing the strip into a strip body, a strip head, and / or a strip tail based on the width increasing inflection points of each of the intersection segment contour features to obtain strip body contour data, strip head contour data, and / or strip tail contour data; Extracting the length value of each second grid in the width direction in the strip body contour data, strip head contour data, and / or strip tail contour data; Based on the length value of each of the first grids in the width direction, performing an equal ratio transformation on the extracted length value of each second grid in the width direction to determine the actual width of the strip.

7. The strip cutting detection method according to claim 3, wherein, The determining the actual distance between the strip head and / or the strip tail and the cutter based on each of the intersection segment contour features and the length value of each of the first grids in the length direction includes: In the case of determining that the strip head and / or the strip tail is detected, dividing the strip into a strip body, a strip head, and / or a strip tail based on the width increasing inflection points of each of the intersection segment contour features, and obtaining strip head contour data and / or strip tail contour data; Based on the strip head contour data and / or the strip tail contour data, extracting the length value of each second grid in the length direction in the strip head contour data and / or the strip tail contour data; Based on the length value of each of the first grids in the length direction, performing an equal ratio transformation on the extracted length value of each second grid in the length direction to determine the actual width of the strip head and / or the strip tail, and the actual distance between the strip head and / or the strip tail and the cutter.

8. The strip cutting detection method according to claim 7, wherein, The extracting the length value of each second grid in the length direction in the strip head contour data and / or the strip tail contour data based on the strip head contour data and / or the strip tail contour data includes; Performing reverse gradient filtering processing on the strip head contour data and / or the strip tail contour data, and extracting the length value of each second grid in the length direction in the strip head contour data and / or the strip tail contour data after the reverse gradient filtering processing.

9. The strip cutting detection method according to claim 6, wherein, The actual width of the strip includes the average width of the strip, the minimum width of the strip, and the maximum width of the strip.

10. A strip cutting detection system, wherein, For applying the strip cutting detection method according to any one of claims 1 to 9, including: At least two image acquisition modules, configured to respectively acquire strip image data and transportation area contour data based on the strip within the transportation area; A control module, electrically connected to the image acquisition modules, configured to control the image acquisition modules to acquire strip image data and transportation area contour data; A processing module, electrically connected to the control module and the image acquisition modules, configured to be controlled by the control module to process the transportation area contour data and the strip image data, so as to respectively determine the actual width of the strip and / or determine the actual distance between the leading end and / or the trailing end of the strip and the cutting tool; An image display module, electrically connected to the control module, configured to perform real-time image display on the transportation area contour data and the strip image data.

Images