A method for positioning a broken edge of a laser light strip phase continuity of a metal plate

Abstract

The application provides a metal plate laser light strip phase continuity broken edge positioning method, and belongs to the technical field of machine vision detection. The method discards the traditional gray gradient detection method, and realizes stable detection of the edge of a high-reflective metal plate by relying on the phase jump feature of the laser light strip. The method filters out background noise by screening effective light strip columns through an adaptive threshold value, avoids the overexposure gray saturation failure problem by solving the phase value through a gray matrix, performs interpolation repair or light supplement and re-shooting on the overexposed phase sequence under different working conditions to ensure data continuity, accurately locates the actual edge of the plate through phase difference, and finally automatically identifies the plate specifications by matching the template library through the phase jump feature. The whole method is not affected by the mirror reflection of the metal plate, has strong detection stability and reliable positioning accuracy, can automatically adapt to plates of different specifications, provides accurate visual data support for subsequent robot automatic grabbing, and improves the real-time performance and robustness of visual detection under high-reflective working conditions.

Description

Technical Field

[0001] This application belongs to the field of machine vision inspection technology, and specifically relates to a method for locating the edge of a broken phase continuity of a laser light stripe on a metal sheet. Background Technology

[0002] In the container manufacturing industry, the roof panels are large-area thin metal sheets coated with anti-rust grease. After being illuminated by a linear laser, large areas of overexposed, saturated mirror-like surfaces are created. Existing industrial visual edge detection methods (Canny operator, Otsu threshold segmentation, traditional laser triangulation, and sub-pixel grayscale edge extraction) all rely on changes in image grayscale gradients to identify the panel contours. In highly reflective, overexposed areas, the image grayscale values ​​saturate, and the gradient information completely disappears, directly causing missed detections and misalignments of the panel edges.

[0003] The existing solution has multiple drawbacks: it has high requirements for camera hardware, requiring industrial cameras with more than 20 megapixels to barely reduce the error; the processing time is as long as 150~250ms, which cannot meet the real-time material handling control cycle of the robot; the positioning error expands to ±2~5mm under overexposure conditions, which cannot meet the high precision requirements of automated handling; when the effective proportion of light stripes is less than 6%, the grayscale histogram segmentation algorithm directly fails. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method for locating the edge of a broken phase of a laser light stripe on a metal sheet, which can identify the boundary of a sudden change in sheet thickness by relying on the coordinate jump of the laser light stripe line, and realize stable, high-precision, and fast edge positioning and automatic specification recognition of the sheet in a high-reflectivity environment.

[0005] This application provides a method for locating the edge of a broken phase continuity laser stripe on a metal sheet, the method comprising the following steps: Images of metal plates with linear laser beams are acquired, and an adaptive filtering threshold is constructed based on the grayscale features of the image columns to filter out the effective image columns carrying the laser beams. For the selected valid image columns, the effective integration interval of the light stripes is automatically defined, and the center coordinates of each laser light stripe column are solved based on gray-scale moment calculation. The center coordinates are defined as the laser phase value to form a phase sequence. Identify and repair overexposure failure columns in the phase sequence; if the number of consecutive overexposure failure columns does not exceed a set threshold, use an interpolation algorithm to complete the phase value; if the number of consecutive overexposure failure columns exceeds the set threshold, re-acquire the image of the metal plate. Perform differential operations on the repaired phase sequence, locate the image coordinates corresponding to the left and right edges of the board based on the peak value of the differential amplitude change, and calculate the actual edge position of the board by combining the camera calibration parameters. The phase transition features whose amplitude exceeds the secondary threshold in the sequence obtained by differential operation are extracted and matched with the pre-stored phase transition template library of sheet metal specifications to obtain the specification model corresponding to the current metal sheet metal.

[0006] In some embodiments, the adaptive filtering threshold is calculated and filtering is performed as follows:

[0007]

[0008] in, Output the pixel grayscale value for coordinates (i, j); The average grayscale value of all pixels in the j-th column; Let the grayscale variance be the value in column j. This represents the total number of rows of pixels used in the calculation for this column; Determine the threshold for valid image columns; This is the variance proportionality coefficient; The mean variance of the background reference column; if The j-th column is the valid image column.

[0009] In some embodiments, the center of the laser stripe is calculated using the following formula:

[0010] in, Let j be the coordinates of the center row of the laser stripe in column j; The zeroth moment represents the total gray energy of the laser stripe. For a first-order moment, the weighted sum of gray levels in the row coordinates; The effective integration interval for the light stripe is automatically defined.

[0011] In some embodiments, the effective integration interval of the light bar is automatically defined by selecting consecutive rows where the absolute value of the difference between the pixel gray level and the column mean exceeds 1.5 times the local standard deviation as the integration interval.

[0012] In some embodiments, linear interpolation or cubic spline interpolation algorithms are used to complete the phase value; if the number of consecutive overexposure failure columns exceeds a set threshold, an auxiliary lighting device is activated to re-acquire the image of the metal plate.

[0013] In some embodiments, the actual edge position of the board is calculated using the following formula:

[0014]

[0015] in, The image column coordinates corresponding to the left and right maximum / peak values ​​are obtained by taking the absolute value of the first-order phase difference between two adjacent columns. , ; To calibrate the scaling factor for the camera; To obtain the actual physical width of the board material.

[0016] In some embodiments, the board specification phase jump template library supports online template updates and the addition of new board specification templates; wherein, the phase jump template for each specification of board is generated by the average value of multiple calibration samples of the corresponding model of board.

[0017] In some embodiments, a device for locating the edge of a broken phase of a laser beam on a metal sheet is also provided, the device comprising: The filtering module is used to acquire images of metal plates that have been shot with a linear laser beam, and to construct an adaptive filtering threshold based on the grayscale features of the image columns to filter out the valid image columns that carry the laser beam. The forming module is used to automatically define the effective integration interval of the light stripes for the selected effective image columns, and solve the center coordinates of each column of laser light stripes based on gray-scale moment calculation, and define the center coordinates as the laser phase value to form a phase sequence; The repair module is used to identify and repair overexposure failure columns in the phase sequence. If the number of consecutive overexposure failure columns does not exceed a set threshold, the phase value is completed using an interpolation algorithm. If the number of consecutive overexposure failure columns exceeds the set threshold, the metal plate image is re-acquired. The conversion module is used to perform differential operations on the repaired phase sequence, locate the image coordinates corresponding to the left and right edges of the board based on the peak value of the differential amplitude change, and calculate the actual edge position of the board by combining the camera calibration parameters. The matching module is used to extract phase transition features whose amplitude exceeds the secondary threshold in the sequence obtained by differential operation, and match them with the pre-stored plate specification phase transition template library to obtain the specification model corresponding to the current metal plate.

[0018] In some embodiments, an electronic device is also provided, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for locating the phase continuity break edge of a laser stripe on a metal sheet as described above are executed.

[0019] In some embodiments, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, performs the steps of the method for locating the phase continuity break edge of a laser stripe on a metal sheet as described in any of the preceding embodiments.

[0020] This application describes a method for locating the edge of a metal sheet where the phase continuity of a laser light stripe is broken. It abandons the traditional grayscale gradient detection method and relies on the phase jump characteristics of the laser light stripe to achieve stable edge detection of highly reflective metal sheets. By using an adaptive threshold to filter out background noise from effective light stripe sequences, and by solving for the phase value using grayscale moments, it avoids overexposure and grayscale saturation failure issues. For different working conditions, it performs interpolation repair or re-exposure to ensure data continuity for overexposed phase sequences. Then, it accurately locates the actual edge of the sheet using phase difference analysis. Finally, it automatically identifies the sheet specifications by matching the phase jump characteristics to a template library. The entire method is unaffected by the specular reflection of the metal sheet, exhibits strong detection stability and reliable positioning accuracy, and can automatically adapt to multiple sheet specifications. This provides accurate visual data support for subsequent automated robotic grasping, improving the real-time performance and robustness of visual inspection under highly reflective conditions. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart of the method for locating the edge of a laser beam phase continuity break in a metal sheet according to an embodiment of this application is shown; Figure 2 A schematic diagram of the structure of the metal sheet laser beam phase continuity breakage edge positioning device according to an embodiment of this application is shown; Figure 3 A schematic diagram of the structure of the electronic device described in an embodiment of this application is shown. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0024] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0025] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0026] To address the shortcomings of existing grayscale visual inspection methods, such as failure, low accuracy, poor real-time performance, and high hardware costs in high-reflectivity metal sheet scenarios, this application provides a method for locating the edge of a broken phase continuity of a laser light stripe on a metal sheet. This method can identify the boundary of a sudden change in sheet thickness by relying on the jump of the laser light stripe line coordinates, and achieve stable, high-precision, and fast edge positioning and automatic specification recognition of the sheet in high-reflectivity environments.

[0027] See the instruction manual appendix Figure 1 This application provides a method for locating the edge of a broken phase continuity of a laser beam on a metal sheet, the method comprising the following steps: S1. Acquire images of metal plates with a linear laser beam, and construct an adaptive filtering threshold based on the grayscale features of the image columns to filter out the effective image columns carrying the laser beam. S2. For the selected effective image columns, the effective integration interval of the light stripes is automatically defined, and the center coordinates of each column of laser light stripes are solved based on the gray-scale moment calculation. The center coordinates are defined as the laser phase value to form a phase sequence. S3. Identify and repair overexposure failure columns in the phase sequence; if the number of consecutive overexposure failure columns does not exceed the set threshold, use an interpolation algorithm to complete the phase value; if the number of consecutive overexposure failure columns exceeds the set threshold, re-acquire the metal plate image. S4. Perform differential operation on the repaired phase sequence, locate the image coordinates corresponding to the left and right edges of the board based on the peak value of the differential amplitude change, and calculate the actual edge position of the board by combining the camera calibration parameters. S5. Extract the phase transition features whose amplitude exceeds the secondary threshold in the sequence obtained by the difference operation, and match them with the pre-stored plate specification phase transition template library to obtain the specification model corresponding to the current metal plate.

[0028] Step S1 mainly involves acquiring the original image of the metal roof with a laser stripe, constructing an adaptive dynamic threshold by calculating the gray-scale variance of each column, filtering out blank background columns without laser illumination and oil noise columns, and retaining only the effective image columns carrying the laser stripe, thereby reducing the amount of subsequent phase extraction calculations and eliminating background gray-scale noise interference.

[0029] Specifically, a linear laser emitter, mounted at a fixed angle to the industrial camera, projects a linear laser beam onto the highly reflective metal sheet, while the 2-megapixel industrial camera simultaneously acquires the image; the grayscale variance of each column of the acquired image is then calculated. ,in, Output the pixel grayscale value for coordinates (i, j); The average grayscale value of all pixels in the j-th column; Let the grayscale variance be the value in column j. This represents the total number of rows of pixels involved in the calculation for this column.

[0030] Real-time extraction of the mean variance of the empty background column in the current frame image According to the formula The adaptive decision threshold is formed, where, This is the variance scaling factor. Only items with a grayscale variance greater than a certain threshold are retained. The image columns are considered valid light bar columns, while the remaining background and noise columns are directly discarded.

[0031] Step S2 mainly targets all valid light stripe columns after step S1, automatically locks the continuous row interval where the laser light stripe is located in each column, calculates the center row coordinates of the laser light stripe based on the zero-order moment and first-order moment of gray level, defines the coordinates as the laser phase value, and generates an ordered and continuous original phase sequence, completely deviating from gray level gradient dependence, and avoiding the high reflectivity overexposure failure problem from the bottom layer.

[0032] Specifically, for a single valid column, the column's grayscale mean and standard deviation are calculated; continuous rows where the absolute value of the difference between the pixel grayscale value and the column mean exceeds 1.5 times the local standard deviation are selected as the grayscale moment integration interval. It eliminates the need for manually preset fixed row ranges and adapts to different laser heights and material placement offsets; within the automatically defined integration interval, it sequentially calculates the grayscale zero-order moment. grayscale first-order moment Then through the formula Solve for the center row coordinates of a single laser stripe and will Defined as laser phase value, all valid column phase values ​​are stored sequentially from smallest to largest according to the image column number. This forms the original phase sequence, which is then passed to the next overexposure repair step.

[0033] Because the anti-rust grease on the surface of the metal top plate can easily cause local specular reflection, the corresponding image column pixels are completely overexposed and saturated, and the effective phase value cannot be calculated, resulting in a break in the phase sequence; step S3 distinguishes between two working conditions: discrete small overexposure and large area continuous overexposure, and processes them separately to restore the integrity and continuity of the phase sequence and avoid losing the edge transition features of the plate in subsequent differential operations.

[0034] Specifically, the original phase sequence output in step S2 is traversed, overexposure failure columns are identified one by one, and the length of consecutive failure columns is counted. A threshold of 20 columns is used to handle two different scenarios: When the number of consecutive overexposure columns is ≤20, the effective phase values ​​on the adjacent left and right sides are used to fill in the missing phase values ​​through either linear interpolation or cubic spline interpolation, smoothly restoring the continuity of the phase sequence. Cubic spline interpolation offers higher repair accuracy and is suitable for scenarios with heavy reflectivity. When the number of consecutive overexposure columns exceeds the 20-column threshold, it is determined that the current imaging reflection interference is too large; the diffuse reflection auxiliary lighting installed on the side of the workstation is automatically triggered to weaken the specular reflection intensity of the substrate, and the laser image is re-acquired. Steps S1 and S2 are repeated to generate the phase sequence. Finally, a complete and unbroken phase sequence after repair is output as the input data source for phase difference calculation.

[0035] Step S4 mainly utilizes the inherent physical characteristic that a sudden change in the thickness of the board material will cause a drastic jump in the laser phase value. It performs differential operations on the repaired continuous phase sequence, extracts the peak value of the phase change, and locates the image coordinates of the left and right edges of the board material. Combined with the camera calibration parameters, the image pixel coordinates are converted into the actual physical width of the board material and the position deviation of the board material relative to the standard station, and outputs high-precision position data that can be used for real-time correction of the robot path.

[0036] Specifically, a first-order phase difference operation is performed on the unbroken phase sequence repaired in step S3. Find the absolute value of the difference, and then find the column coordinates corresponding to the peak values ​​of the two maximum values ​​of the amplitude. , The position is determined by the pixel position of the left and right edges of the board material; then the calibration conversion formula is used. Calculate the actual physical width of the board material ,in, The pixel-to-millimeter ratio coefficient obtained from camera calibration is used to calculate the material offset relative to the standard station based on the edge pixel coordinates. After the calculation is completed, the position deviation is sent to the downstream robot scheduling system to correct the motion path, and the entire phase difference sequence is output to the specification recognition step. The entire process from step S1 to step S4 takes ≤20ms per process.

[0037] Step S5 mainly extracts the effective transition features from the phase difference sequence output in step S4, matches them with the pre-stored specification template library, automatically identifies the top plate models of 20-foot, 40-foot, and 53-foot containers, and matches the corresponding suction cup partitions, material handling coordinates, and top plate placement order for the downstream dual-robot system to adaptive gripping process parameters.

[0038] Specifically, a secondary amplitude threshold is first set, retaining only the peak points of the phase difference whose absolute value exceeds this threshold. These selected peak points constitute a unique characteristic phase transition sequence for the current material. The characteristic transition sequence of the material extracted in real-time is compared with all standard templates in the template library for each specification. The result with the highest matching degree is output as the specification model of the current material. Regarding the standard template construction rules, for each container roof specification that needs to be identified, at least 20 repeated sampling tests are performed during the equipment calibration and debugging phase. The arithmetic mean of multiple sets of characteristic transition sequences collected for the same specification is calculated to generate the corresponding standard phase transition template and store it in the database. Simultaneously, this specification characteristic phase transition template library is equipped with a version management mechanism. Existing template parameters can be updated and corrected online via a human-machine interface touchscreen. It can also expand the database by adding standard templates for new material models, meeting the needs of subsequent iterative expansion of material models in the container production line.

[0039] This application provides a method for locating the edge of a broken laser beam phase in metal sheets. First, it filters effective laser beam image columns by using an adaptive threshold for column grayscale variance to remove background noise. Second, it calculates the center coordinates of the laser beam column by column using a grayscale moment algorithm and defines them as phase values, constructing an original phase sequence. Then, based on the number of consecutive overexposed columns, it repairs the broken phase sequence using interpolation or re-enhancing methods. Next, it performs a first-order difference operation on the complete phase sequence, locating the sheet edge based on the phase jump peak, and calculates the actual width and material offset using camera calibration coefficients. Finally, it extracts the differential jump features and matches them with a specification template library constructed from multiple sets of calibration averages to automatically identify 20-foot, 40-foot, and 53-foot container top plate models. This method avoids interference from high-reflectivity overexposure by relying on the phase jump principle. The algorithm takes ≤20ms per run, achieves edge positioning accuracy of ±1mm, supports online updates and expansion of the template library, and exhibits strong robustness and real-time performance. It can provide accurate visual data for dual-robot collaborative handling systems and is suitable for online inspection scenarios of sheet metal in automated container production lines.

[0040] Based on the same inventive concept, this application also provides a device for locating the edge of a broken phase continuity of a laser stripe on a metal sheet. Since the principle of the device in this application is similar to the above-mentioned method for locating the edge of a broken phase continuity of a laser stripe on a metal sheet, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0041] As per the instruction manual Figure 2 As shown in the figure, this application embodiment also provides a device for locating the edge of a broken phase continuity of a laser beam on a metal sheet, the device comprising: The filtering module 201 is used to acquire images of metal plates that have been shot with a line of laser light stripes, and to construct an adaptive filtering threshold based on the grayscale features of the image columns to filter out the effective image columns that carry the laser light stripes. The forming module 202 is used to automatically define the effective integration interval of the light stripes for the selected effective image columns, and solve the center coordinates of each column of laser light stripes based on gray-scale moment calculation, and define the center coordinates as the laser phase value to form a phase sequence; Repair module 203 is used to identify and repair overexposure failure columns in the phase sequence; wherein, if the number of consecutive overexposure failure columns does not exceed a set threshold, the phase value is completed using an interpolation algorithm; if the number of consecutive overexposure failure columns exceeds the set threshold, the metal plate image is re-acquired. The conversion module 204 is used to perform differential operations on the repaired phase sequence, locate the image coordinates corresponding to the left and right edges of the board based on the peak value of the differential amplitude change, and calculate the actual edge position of the board by combining the camera calibration parameters. The matching module 205 is used to extract phase transition features whose amplitude exceeds the secondary threshold in the sequence obtained by differential operation, and match them with the pre-stored plate specification phase transition template library to obtain the specification model corresponding to the current metal plate.

[0042] In some embodiments, the adaptive filtering threshold is calculated and filtering is performed as follows:

[0043]

[0044] in, Output the pixel grayscale value for coordinates (i, j); The average grayscale value of all pixels in the j-th column; Let the grayscale variance be the value in column j. This represents the total number of rows of pixels used in the calculation for this column; Determine the threshold for valid image columns; This is the variance proportionality coefficient; The mean variance of the background reference column; if The j-th column is the valid image column.

[0045] In some embodiments, the center of the laser stripe is calculated using the following formula:

[0046] in, Let j be the coordinates of the center row of the laser stripe in column j; The zeroth moment represents the total gray energy of the laser stripe. For a first-order moment, the weighted sum of gray levels in the row coordinates; The effective integration interval for the light stripe is automatically defined.

[0047] In some embodiments, the effective integration interval of the light bar is automatically defined by selecting consecutive rows where the absolute value of the difference between the pixel gray level and the column mean exceeds 1.5 times the local standard deviation as the integration interval.

[0048] In some embodiments, linear interpolation or cubic spline interpolation algorithms are used to complete the phase value; if the number of consecutive overexposure failure columns exceeds a set threshold, an auxiliary lighting device is activated to re-acquire the image of the metal plate.

[0049] In some embodiments, the actual edge position of the board is calculated using the following formula:

[0050]

[0051] in, The image column coordinates corresponding to the left and right maximum / peak values ​​are obtained by taking the absolute value of the first-order phase difference between two adjacent columns. , ; To calibrate the scaling factor for the camera; To obtain the actual physical width of the board material.

[0052] In some embodiments, the board specification phase jump template library supports online template updates and the addition of new board specification templates; wherein, the phase jump template for each specification of board is generated by the average value of multiple calibration samples of the corresponding model of board.

[0053] The metal sheet laser beam phase continuity breakage edge positioning device described in this application acquires images of metal sheets with a linear laser beam through a screening module, and constructs an adaptive screening threshold based on the grayscale features of the image columns to screen out the effective image columns carrying the laser beam. A forming module automatically delineates the effective integration interval of the beam through the screened effective image columns, and calculates the center coordinates of each laser beam column based on grayscale moment calculation. These center coordinates are defined as the laser phase value, forming a phase sequence. A repair module identifies and repairs overexposed failure columns in the phase sequence. If the number of consecutive overexposed failure columns does not exceed a set threshold, an interpolation algorithm is used to complete the phase value. If the number of consecutive overexposed failure columns exceeds the set threshold, the metal sheet image is re-acquired. A conversion module performs differential calculations on the repaired phase sequence, locates the image coordinates corresponding to the left and right edges of the sheet based on the peak value of the differential amplitude change, and calculates the actual edge position of the sheet by combining camera calibration parameters. A matching module extracts phase jump features in the sequence obtained from the differential calculation whose amplitude exceeds a secondary threshold, and matches them with a pre-stored sheet specification phase jump template library to obtain the specification model corresponding to the current metal sheet. By relying on the coordinate jump of the laser light stripe to identify the boundary of the sudden change in the thickness of the board, it can achieve stable, high-precision, and fast edge positioning and automatic specification recognition of the board in a highly reflective environment.

[0054] Based on the same concept of the present invention, as shown in the appendix to the specification. Figure 3 As shown in the figure, an embodiment of this application provides the structure of an electronic device 300, which includes: at least one processor 301, at least one network interface 304 or other user interface 303, memory 305, and at least one communication bus 302. The communication bus 302 is used to realize the connection and communication between these components. The electronic device 300 may optionally include a user interface 303, including a display (e.g., touch screen, LCD, CRT, holographic imaging, or projector, etc.), a keyboard, or a clicking device (e.g., mouse, trackball, touchpad, or touch screen, etc.).

[0055] Memory 305 may include read-only memory and random access memory, and provides instructions and data to processor 301. A portion of memory 305 may also include non-volatile random access memory (NVRAM).

[0056] In some implementations, memory 305 stores executable modules or data structures, or subsets thereof, or extended sets thereof: The 3051 operating system contains various system programs used to implement various basic business functions and handle hardware-based tasks. Application module 3052 contains various applications, such as desktop (launcher), media player (MediaPlayer), browser (Browser), etc., to implement various application services.

[0057] In this embodiment of the application, by calling the program or instructions stored in the memory 305, the processor 301 is used to execute the steps of a method for locating the broken edge of the phase continuity of a laser stripe on a metal sheet.

[0058] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs steps such as those in a method for locating the broken edge of a laser stripe phase continuity in a metal sheet.

[0059] Specifically, the storage medium can be a general-purpose storage medium, such as a portable disk or hard disk. When the computer program on the storage medium is run, it can identify the boundary of sudden changes in the thickness of the board material by relying on the coordinate jump of the laser light strip, so as to achieve stable, high-precision, and fast edge positioning and automatic specification identification of the board material in a high-reflectivity environment.

[0060] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interface, and the indirect coupling or communication connection of the apparatus or units may be electrical, mechanical, or other forms.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0062] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0063] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] Finally, it should be noted that the above embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for locating the edge of a laser beam phase continuity break in a metal sheet, characterized in that, The method includes the following steps: Images of metal plates with linear laser beams are acquired, and an adaptive filtering threshold is constructed based on the grayscale features of the image columns to filter out the effective image columns carrying the laser beams. For the selected valid image columns, the effective integration interval of the light stripes is automatically defined, and the center coordinates of each laser light stripe column are solved based on gray-scale moment calculation. The center coordinates are defined as the laser phase value to form a phase sequence. Identify and repair overexposure failure columns in the phase sequence; if the number of consecutive overexposure failure columns does not exceed a set threshold, use an interpolation algorithm to complete the phase value; if the number of consecutive overexposure failure columns exceeds the set threshold, re-acquire the image of the metal plate. Perform differential operations on the repaired phase sequence, locate the image coordinates corresponding to the left and right edges of the board based on the peak value of the differential amplitude change, and calculate the actual edge position of the board by combining the camera calibration parameters. The phase transition features whose amplitude exceeds the secondary threshold in the sequence obtained by differential operation are extracted and matched with the pre-stored phase transition template library of sheet metal specifications to obtain the specification model corresponding to the current metal sheet metal.

2. The method for locating the edge of a laser beam phase continuity break in a metal sheet according to claim 1, characterized in that, The adaptive filtering threshold is calculated and filtered as follows: in, Output the pixel grayscale value for coordinates (i, j); The average grayscale value of all pixels in the j-th column; Let the grayscale variance be the value in column j. This represents the total number of rows of pixels used in the calculation for this column; Determine the threshold for valid image columns; This is the variance proportionality coefficient; The mean variance of the background reference column; if The j-th column is the valid image column.

3. The method for locating the edge of a laser beam phase continuity break in a metal sheet according to claim 2, characterized in that, The center of the laser stripe is calculated using the following formula: in, Let j be the coordinates of the center row of the laser stripe in column j; The zeroth moment represents the total gray energy of the laser stripe. For a first-order moment, the weighted sum of gray levels in the row coordinates; The effective integration interval for the light stripe is automatically defined.

4. The method for locating the edge of a laser beam phase continuity break in a metal sheet according to claim 3, characterized in that, in, The method for automatically defining the effective integration interval of the light bar is as follows: select continuous rows where the absolute value of the difference between the pixel gray level and the column mean exceeds 1.5 times the local standard deviation as the integration interval.

5. The method for locating the edge of a laser beam phase continuity break in a metal sheet according to claim 3, characterized in that, in, The phase value is completed using linear interpolation or cubic spline interpolation algorithms; if the number of consecutive overexposure failure columns exceeds the set threshold, the auxiliary lighting device is activated to re-acquire the image of the metal plate.

6. The method for locating the edge of a broken phase of a laser beam stripe on a metal sheet according to claim 5, characterized in that, The actual edge position of the board material is calculated using the following formula: in, The image column coordinates corresponding to the left and right maximum / peak values ​​are obtained by taking the absolute value of the first-order phase difference between two adjacent columns. , ; To calibrate the scaling factor for the camera; To obtain the actual physical width of the board material.

7. A method for locating the edge of a broken phase of a laser beam stripe on a metal sheet according to claim 6, characterized in that, The board specification phase jump template library supports online template updates and the addition of new board specification templates; the phase jump template for each specification of board is generated by the average value of multiple calibration samples of the corresponding model of board.

8. A device for locating the edge of a laser beam phase continuity break in a metal sheet, characterized in that, The device includes: The filtering module is used to acquire images of metal plates that have been shot with a linear laser beam, and to construct an adaptive filtering threshold based on the grayscale features of the image columns to filter out the valid image columns that carry the laser beam. The forming module is used to automatically define the effective integration interval of the light stripes for the selected effective image columns, and solve the center coordinates of each column of laser light stripes based on gray-scale moment calculation, and define the center coordinates as the laser phase value to form a phase sequence; The repair module is used to identify and repair overexposure failure columns in the phase sequence. If the number of consecutive overexposure failure columns does not exceed a set threshold, the phase value is completed using an interpolation algorithm. If the number of consecutive overexposure failure columns exceeds the set threshold, the metal plate image is re-acquired. The conversion module is used to perform differential operations on the repaired phase sequence, locate the image coordinates corresponding to the left and right edges of the board based on the peak value of the differential amplitude change, and calculate the actual edge position of the board by combining the camera calibration parameters. The matching module is used to extract phase transition features whose amplitude exceeds the secondary threshold in the sequence obtained by differential operation, and match them with the pre-stored plate specification phase transition template library to obtain the specification model corresponding to the current metal plate.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the method for locating the phase continuity break edge of a laser stripe on a metal sheet as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method for locating the phase continuity break edge of a laser stripe on a metal sheet as described in any one of claims 1 to 7.

Images