Plate size measurement method and system based on three-dimensional modeling

Abstract

The invention relates to the technical field of plate measurement, and relates to a plate size measurement method and system based on three-dimensional modeling, and the method comprises the steps: determining at least three non-linear reference points on a roller of a roller path, and obtaining a three-dimensional model of the roller; obtaining a first coordinate of a nonlinear reference point measured by a laser scanner; obtaining a corresponding second coordinate of a nonlinear reference point in the three-dimensional model; calculating a coordinate transformation matrix according to the first coordinate and the second coordinate of the nonlinear reference point; acquiring a plurality of acquisition coordinate points on the upper surface of the roller of the roller path acquired by the laser scanner, converting the acquisition coordinate points into coordinate points in a model coordinate system through a coordinate transformation matrix, and recording the coordinate points as model coordinate points; screening model coordinate points whose distances to the three-dimensional model are greater than a preset distance threshold, and recording the model coordinate points as target model coordinate points; and calculating the size of the plate. According to the invention, the size of the plate can be accurately measured in a poor illumination environment.

Description

Technical Field

[0001] The present invention relates to the technical field of sheet metal measurement. More specifically, the present invention relates to a method and system for measuring the dimensions of a sheet metal based on three-dimensional modeling. Background Art

[0002] In the field of sheet metal processing, dimension measurement is an important link to ensure the accuracy and quality of products. Traditional dimension measurement methods are contact measurement methods such as using mechanical measuring tools or coordinate measuring machines (CMMs). Among them, the accuracy of manual measurement using mechanical measuring tools such as vernier calipers and micrometers is usually ±0.5 mm, which is suitable for rough machining scenarios, but has low efficiency and relies on manual experience.

[0003] With the continuous improvement of the precision requirements of industrial manufacturing, many modern processing processes now begin to adopt more efficient and accurate measurement technologies. For example, high-resolution cameras are used to collect images, and image processing algorithms are used to analyze the dimensions of the sheet metal (such as length, width, and thickness), support dynamic detection and automatic comparison with the design values, and the efficiency is several times higher than that of manual labor.

[0004] However, in some complex processing scenarios (such as the influence of environmental factors such as light changes and surface reflections), errors in image acquisition may occur, which may affect the accuracy of the sheet metal measurement results. Moreover, the presence of stains, scratches, or uneven colors on the surface of the sheet metal (especially at the edges of the sheet metal) may also affect the accuracy of determining the boundaries of the sheet metal through images, thereby affecting the accuracy of the sheet metal dimension measurement. Summary of the Invention

[0005] To solve the technical problem that factors such as the above processing environment may affect the accuracy of identifying the dimensions of a sheet metal through the sheet metal image, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a method for measuring the size of a sheet based on three-dimensional modeling includes: determining at least three non-linear reference points on the rollers of a raceway and obtaining a three-dimensional model of the rollers of the raceway, where the three non-linear reference points are not coplanar; obtaining the first coordinates of the non-linear reference points measured by a laser scanner, where the laser of the laser scanner is emitted towards the ground plane and the emission direction is perpendicular to the ground plane; obtaining the second coordinates of the non-linear reference points in the three-dimensional model; calculating a coordinate transformation matrix based on the first coordinates and the second coordinates of the non-linear reference points, where the coordinate transformation matrix is used to map the coordinates measured by the laser scanner into the model coordinate system in which the three-dimensional model is located; obtaining a plurality of acquisition coordinate points on the upper surface of the rollers of the raceway collected by the laser scanner and converting the acquisition coordinate points into coordinate points in the model coordinate system through the coordinate transformation matrix, denoted as model coordinate points; screening out the model coordinate points whose distance from the three-dimensional model is greater than a preset distance threshold, denoted as target model coordinate points; and obtaining the size of the sheet based on the target model coordinate points.

[0007] Preferably, calculating the coordinate transformation matrix includes: Constructing an equation: , where , , , , , , , , , , and are all matrix parameters, i = 1, 2, or 3, the first coordinate of the first non-linear reference point is , the first coordinate of the second non-linear reference point is , the first coordinate of the third non-linear reference point is , the second coordinate of the first non-linear reference point is , the second coordinate of the second non-linear reference point is , the second coordinate of the third non-linear reference point is ; after solving the equation and obtaining the matrix parameters, obtaining the coordinate transformation matrix: , where M is the coordinate transformation matrix.

[0008] Preferably, converting the i th acquisition coordinate point into the coordinates in the model coordinate system through the coordinate transformation matrix to obtain the i th model coordinate point includes: taking as the i th acquisition coordinate point, is the i th model coordinate point. Solve the formula i according to the th acquisition coordinate point and the coordinate transformation matrix to obtain the i th model coordinate point.

[0009] Preferably, the three-dimensional model includes a plurality of polygon patches. Calculating the distance between any model coordinate point and the three-dimensional model includes: taking the model coordinate point as the center and making a circle with a radius of r , where r is a preset value; determining the polygon patches that intersect with the circle and the polygon patches inside the circle as the adjacent patches of the model coordinate point; calculating the distance between the model coordinate point and its adjacent patches; determining the minimum value among the distances between the model coordinate point and all its adjacent patches as the distance between the model coordinate point and the three-dimensional model.

[0010] Preferably, in response to the number of polygon patches that intersect with the circle and the number of polygon patches inside the circle both being 0, after increasing the value of the radius at the current moment by a preset multiple, make a circle with the model coordinate point as the center and perform iteration; in response to the number of polygon patches that intersect with the circle or the number of polygon patches inside the circle being greater than or equal to 1, stop the iteration.

[0011] Preferably, calculating the distance between the j th model coordinate point and its p th adjacent patch includes: obtaining the projection point of the j th model coordinate point on the plane where its p th adjacent patch is located; in response to the projection point being located in the j th adjacent patch of the p th model coordinate point, calculate the distance between the j th model coordinate point and its p th adjacent patch, where the calculation formula is: ; is the j th normal vector of the plane where the p th adjacent patch of the th model coordinate point is located, j is the j th model coordinate point; in response to the projection point being located in the p th adjacent patch of the j th model coordinate point, calculate the distance between the p th model coordinate point and its ; is the j distance between the p th model coordinate point and the q th vertex of its th adjacent patch, j is the p distance between the q th model and the n th edge of its j th adjacent patch, p is the number of vertices of the

[0012] Preferably, the dimensions of the plate include the width, length, and thickness of the plate. Obtaining the dimensions of the plate according to the target model coordinate points includes: fitting the target model coordinate points to obtain a fitted polygon; determining that the product of the length of the polygon and the proportionality coefficient corresponding to the three-dimensional model is the length of the plate, and determining that the product of the width of the polygon and the proportionality coefficient corresponding to the three-dimensional model is the width of the plate; screening out the vertices of multiple polygon patches, denoted as target vertices, where the projection points of the target vertices on the plane where the fitted polygon is located are within the fitted polygon; obtaining the distances between all the target vertices and the fitted polygon, denoted as target distances; performing clustering processing on the target distances to obtain multiple classification clusters, calculating the mean of all the target distances in each classification cluster, and determining that the product of the minimum value of the means corresponding to all the classification clusters and the proportionality coefficient corresponding to the three-dimensional model is the thickness of the plate.

[0013] Preferably, the target model coordinate points are fitted into a polygon by the RANSAC algorithm.

[0014] Preferably, a method for measuring the dimensions of a plate based on three-dimensional modeling further includes: performing data cleaning on the target model coordinate points before fitting the target model coordinate points to obtain a fitted polygon.

[0015] In a second aspect, a system for measuring the dimensions of a plate based on three-dimensional modeling includes a processor and a memory. The memory stores a computer program, and is characterized in that the processor executes the computer program to implement a method for measuring the dimensions of a plate based on three-dimensional modeling as described in any one of the above-mentioned invention contents.

[0016] The beneficial effects of the present invention are as follows: The present invention constructs a three-dimensional model and uses the coordinate data collected by a laser scanner. Combining with the coordinate transformation matrix, it maps the coordinates measured by the laser scanner into the coordinate system of the three-dimensional model, and calculates the efficiency of sheet size measurement based on automated coordinate transformation, screening, and fitting algorithms, reducing manual intervention and improving the automation level of the measurement process. Since the present invention does not require real-time acquisition of images of the sheet, and the present invention determines the position and size of the sheet by laser, the present invention can still accurately measure the size of the sheet in the case of defects such as stains, scratches, or uneven color on the surface of the sheet or poor lighting conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of illustration and not limitation, and like or corresponding reference numerals indicate like or corresponding parts, wherein: Figure 1 is a flowchart showing the steps of a method for measuring the size of a sheet based on three-dimensional modeling according to an embodiment of the present invention; Figure 2 is a schematic diagram of a three-dimensional model of a roller of a raceway according to an embodiment of the present invention; Figure 3 is a block diagram showing the structure of a system for measuring the size of a sheet based on three-dimensional modeling according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0019] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings.

[0020] Figure 1 is a flowchart showing the steps of a method for measuring the size of a sheet based on three-dimensional modeling according to an embodiment of the present invention.

[0021] As Figure 1 shown, a method for measuring the size of a sheet based on three-dimensional modeling includes steps S1 to S7.

[0022] Step S1: Determine at least three non-linear reference points on the roller of the raceway and obtain a three-dimensional model of the roller of the raceway.

[0023] Among them, the three non-linear reference points are not coplanar.

[0024] Figure 2 It is a schematic diagram of a three-dimensional model of a raceway according to an embodiment of the present invention.

[0025] As Figure 2 shown, the raceway includes a plurality of rollers, and the sheet is transported by the rotation of the rollers. The three-dimensional model mentioned in this application only includes the roller part in the three-dimensional model of the raceway.

[0026] Step S2: Obtain the first coordinates of the non-linear reference points measured by the laser scanner.

[0027] Wherein the laser of the laser scanner is emitted towards the ground plane and the emission direction is perpendicular to the ground plane.

[0028] It should be noted that the working principle of the laser scanner is as follows: The laser scanner determines the spatial position of the target point by emitting a laser beam and measuring the time difference or reflection intensity of the return signal. The laser scanner generally provides the three-dimensional coordinates of each measurement point in space. Coordinate system: The coordinate system of the laser scanner is usually based on the local coordinate system of the instrument, where the laser is emitted towards the ground plane and the emission direction is perpendicular to the ground plane, ensuring that the coordinate points on the upper surface of the sheet can be collected.

[0029] Step S3: Obtain the corresponding second coordinates of the non-linear reference points in the three-dimensional model, and calculate the coordinate transformation matrix according to the first coordinates and the second coordinates of the non-linear reference points.

[0030] It should be noted that the coordinate transformation matrix is used to describe the conversion relationship from one coordinate system to another. Among them, the coordinate transformation matrix in the present invention is used to map the coordinates measured by the laser scanner into the model coordinate system where the three-dimensional model is located.

[0031] In one embodiment, calculating the coordinate transformation matrix includes: Construct an equation: , where , , , , , , , , , , and are all matrix parameters, i = 1, 2 or 3, the first coordinate of the first non-linear reference point is , the first coordinate of the second non-linear reference point is , the first coordinate of the third non-linear reference point is , the second coordinate of the first non-linear reference point is , the second coordinate of the second non-linear reference point is , the second coordinate of the third non-linear reference point is ; After solving the equation and obtaining the matrix parameters, the coordinate transformation matrix is obtained: , where M is the coordinate transformation matrix.

[0032] Step S4: Obtain multiple acquisition coordinate points on the upper surface of the roller of the raceway collected by the laser scanner, and convert the acquisition coordinate points into coordinate points in the model coordinate system through the coordinate transformation matrix, denoted as model coordinate points.

[0033] In one embodiment, the i th acquisition coordinate point is converted into the coordinates in the model coordinate system to obtain the i th model coordinate point, including: taking as the i th acquisition coordinate point, as the i th model coordinate point, and solving the formula i according to the th acquisition coordinate point and the coordinate transformation matrix to obtain the i th model coordinate point.

[0034] It should be noted that the coordinate transformation matrix is a homogeneous transformation matrix, and through the coordinate transformation matrix, the acquisition coordinate points collected by the laser scanner can be subjected to affine transformation to obtain the coordinate points in the coordinate system where the three-dimensional model is located.

[0035] Among them, affine transformation (Affine Transformation) is the superposition of linear transformation and translation transformation. Affine transformation includes scaling (Scale), translation (transform), rotation (rotate), reflection (reflection), and shear mapping (shear mapping).

[0036] Step S5: Screen out the model coordinate points whose distance from the three-dimensional model is greater than a preset distance threshold, denoted as target model coordinate points.

[0037] It should be noted that the model coordinate points are converted from the collected coordinate points. If a collected coordinate point is obtained by a laser scanner scanning the upper surface of the plate, there is a certain distance between the model coordinate point converted from this collected coordinate point and the 3D model; if a collected coordinate point is obtained by a laser scanner scanning the raceway, there is almost no distance between the model coordinate point converted from this collected coordinate point and the 3D model. Based on this, the target model coordinate points belong to the model coordinate points converted from the collected coordinate points obtained by the laser scanner scanning the upper surface of the plate, and the size of the plate can be obtained according to the target model coordinate points.

[0038] In one embodiment, the 3D model includes a plurality of polygon meshes, and calculating the distance between any model coordinate point and the 3D model includes: taking the model coordinate point as the center of a circle and making a circle with a radius of r , where r is a preset value; determining the polygon meshes that intersect with the circle and the polygon meshes inside the circle as the adjacent meshes of the model coordinate point; calculating the distance between the model coordinate point and its adjacent meshes; and determining the minimum value among the distances between the model coordinate point and all its adjacent meshes as the distance between the model coordinate point and the 3D model.

[0039] It should be noted that by constructing a circle with the model coordinate point as the center, the polygon meshes closer to the model coordinate point can be screened out, which is convenient for calculating the distance between the model coordinate point and the 3D model.

[0040] Furthermore, the distance between the model coordinate point and the 3D model is the In one embodiment, calculating the distance between the j th model coordinate point and its p th adjacent mesh includes: obtaining the projection point of the j th model coordinate point on the plane of its p th adjacent mesh; in response to the projection point being located in the j th model coordinate point's p th adjacent mesh, calculating the distance between the j th model coordinate point and its p th adjacent mesh, where the calculation formula is: ; is the normal vector of the plane of the j th model coordinate point's p th adjacent mesh, is the j th model coordinate point; in response to the projection point being located in the j th model coordinate point's p th adjacent mesh, calculating thej The distance between a model coordinate point and its p th adjacent patch, where the calculation formula is: ; is the j th distance between a model coordinate point and the p th vertex of its q th adjacent patch, is the j th distance between a model and the p th edge of its q th adjacent patch, n is the j th distance between a model coordinate point and the p number of vertices of its

[0041] Among them, in response to the number of polygon patches that intersect with the circle and the number of polygon patches inside the circle both being 0, after increasing the value of the radius at the current moment by a preset multiple, a circle is drawn with the model coordinate point as the center for iteration; in response to the number of polygon patches that intersect with the circle or the number of polygon patches inside the circle being greater than or equal to 1, the iteration stops. Based on this, it can be ensured that the model coordinate point obtains at least one adjacent patch.

[0042] Step S6: Obtain the size of the sheet according to the target model coordinate point.

[0043] In one embodiment, the size of the sheet includes the width, length, and thickness of the sheet. Obtaining the size of the sheet according to the target model coordinate point includes: fitting the target model coordinate point to obtain a fitting polygon; determining that the product of the length of the polygon and the proportionality coefficient corresponding to the three-dimensional model is the length of the sheet, and determining that the product of the width of the polygon and the proportionality coefficient corresponding to the three-dimensional model is the width of the sheet; screening out the vertices of multiple polygon patches, denoted as target vertices, where the projection points of the target vertices on the plane where the fitting polygon is located are within the fitting polygon; obtaining the distances between all the target vertices and the fitting polygon, denoted as target distances; performing clustering processing on the target distances to obtain multiple classification clusters, calculating the mean of all the target distances in each classification cluster, and determining that the product of the minimum value of the means corresponding to all the classification clusters and the proportionality coefficient corresponding to the three-dimensional model is the thickness of the sheet.

[0044] It should be noted that the proportionality coefficient is the mapping between the model and the real world, and the proportionality coefficient is used to adjust the size of the model to the actual size in the real world.

[0045] Among them, when clustering the target distances, a difference threshold needs to be determined. The difference threshold is used to judge whether the target distances belong to the same classification cluster. If the difference between two target distances is small, they belong to the same cluster. In one embodiment, the proportionality coefficient is 100, and the difference threshold is 0.03 mm.

[0046] It should be noted that the minimum value of the means corresponding to all classification clusters, that is, the mean of the distances between the points closest to the distance polygon (fitted from the target model coordinate points) in the three-dimensional model and the three-dimensional model. The points closest to the distance polygon in the three-dimensional model are mapped to the roller track for transporting the sheet material, which is the points on the upper side of the roller closely attached to the lower surface of the sheet material. Therefore, the minimum value of the means corresponding to all classification clusters is the width of the sheet material.

[0047] In one embodiment, the target model coordinate points are fitted into a polygon by the RANSAC algorithm. Before fitting the target model coordinate points to obtain a fitted polygon, data cleaning is performed on the target model coordinate points.

[0048] Figure 3 It schematically shows the structural block diagram of a sheet material size measurement system based on three-dimensional modeling according to this embodiment.

[0049] The present invention also provides a sheet material size measurement system based on three-dimensional modeling. As Figure 3 shown, the system includes a processor and a memory. The memory stores computer program instructions. When the computer program instructions are executed by the processor, it realizes a sheet material size measurement method according to the first aspect of the present invention.

[0050] The system also includes other components well-known to those skilled in the art such as a communication interface. Its settings and functions are known in the art, so they will not be elaborated here.

[0051] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as, resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that can be stored or otherwise held by such a computer-readable medium.

[0052] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, for example, two, three, or more, etc., unless otherwise specifically defined.

[0053] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and concept of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be adopted in the process of practicing the present invention.

Claims

1. A method for measuring the size of a sheet based on three-dimensional modeling, characterized in that, Including: Determine at least three non-linear reference points on the roller of the raceway and obtain a three-dimensional model of the roller of the raceway, where the three non-linear reference points are not coplanar; Obtain the first coordinates of the non-linear reference points measured by the laser scanner, where the laser of the laser scanner is emitted towards the ground plane and the emission direction is perpendicular to the ground plane; obtain the second coordinates of the non-linear reference points in the three-dimensional model; calculate a coordinate transformation matrix according to the first coordinates and the second coordinates of the non-linear reference points, where the coordinate transformation matrix is used to map the coordinates measured by the laser scanner into the model coordinate system where the three-dimensional model is located; Obtain a plurality of acquisition coordinate points on the upper surface of the roller of the raceway collected by the laser scanner, and convert the acquisition coordinate points into coordinate points in the model coordinate system through the coordinate transformation matrix, denoted as model coordinate points; Screen out the model coordinate points whose distance from the three-dimensional model is greater than a preset distance threshold, denoted as target model coordinate points [1]; Obtain the size of the sheet according to the target model coordinate points.

2. The method for measuring the size of a sheet based on three-dimensional modeling according to claim 1, characterized in that, Calculating the coordinate transformation matrix includes: Construct the equation: , where , , , , , , , , , , and are all matrix parameters; wherein, i = 1, 2, or 3, the first coordinate of the first non-linear reference point is and the first coordinate of the second non-linear reference point is and the first coordinate of the third non-linear reference point is ; the second coordinate of the first non-linear reference point is and the second coordinate of the second non-linear reference point is and the second coordinate of the third non-linear reference point is ; After solving the equation and obtaining the matrix parameters, the coordinate transformation matrix is obtained: , where M is the coordinate transformation matrix.

3. A method for measuring the size of a sheet based on three-dimensional modeling according to claim 2, characterized in that, Convert the i th acquired coordinate point to the coordinate in the model coordinate system to obtain the i th model coordinate point, including: Taking as the i th acquisition coordinate point, as the i th model coordinate point, according to the i th acquisition coordinate point and the coordinate transformation matrix, solve the formula to obtain the i th model coordinate point.

4. A method for measuring the size of a sheet based on three-dimensional modeling according to claim 1, characterized in that, The three-dimensional model includes a plurality of polygon patches, where calculating the distance between any model coordinate point and the three-dimensional model includes: Taking the model coordinate point as the center, draw a circle with a radius of r , where r is a preset value; Determine the polygon patches that intersect with the circle and the polygon patches inside the circle as the adjacent patches of the model coordinate point; Calculate the distance between the model coordinate point and its adjacent patches; Determine the minimum value among the distances between the model coordinate point and all its adjacent patches as the distance between the model coordinate point and the three-dimensional model.

5. A method for measuring the size of a sheet based on three-dimensional modeling according to claim 4, characterized in that, In response to the number of polygon patches that intersect with the circle and the number of polygon patches inside the circle both being 0, after increasing the value of the radius by a preset multiple at the current moment, make a circle with the model coordinate point as the center and perform iteration; in response to the number of polygon patches that intersect with the circle or the number of polygon patches inside the circle being greater than or equal to 1, stop the iteration.

6. A method for measuring the size of a plate based on three-dimensional modeling according to claim 4, characterized in that, Calculate the j distance between the p th adjacent patch of the model coordinate point, including: Obtain the j model coordinate point's projection point on the plane where its p th adjacent patch is located; In response to the projection point being located in the j th adjacent patch of the p th model coordinate point, calculate the distance between the j th model coordinate point and its p th adjacent patch, where the calculation formula is: ； is the j normal vector of the plane where the p th adjacent patch of the th model coordinate point is located, j where the th model coordinate point is; In response to the projection point being located in the j th adjacent patch of the p th model coordinate point, calculate the distance between the j th model coordinate point and its p th adjacent patch, where the calculation formula is: ； is the distance between the j th model coordinate point and the p th vertex of its q th adjacent patch, is the distance between the j th model and the p th edge of its q th adjacent patch, n is the number of vertices of the j th model coordinate point and its p th adjacent patch.

7. A method for measuring the size of a sheet based on three-dimensional modeling according to claim 4, characterized in that The size of the sheet includes the width, length and thickness of the sheet, and obtaining the size of the sheet according to the target model coordinate points includes: Fit the target model coordinate points to obtain a fitted polygon; determine the product of the length of the polygon and the corresponding scale factor of the three-dimensional model as the length of the sheet, and determine the product of the width of the polygon and the corresponding scale factor of the three-dimensional model as the width of the sheet; Screen out the vertices of a plurality of polygon patches, denoted as target vertices, where the projection points of the target vertices on the plane where the fitted polygon is located are within the fitted polygon; Obtain the distances between all the target vertices and the fitted polygon, denoted as target distances; perform clustering processing on the target distances to obtain a plurality of classification clusters, calculate the mean of all the target distances in each classification cluster, and determine the product of the minimum value of the means corresponding to all the classification clusters and the corresponding scale factor of the three-dimensional model as the thickness of the sheet.

8. A method for measuring the size of a sheet based on 3D modeling according to claim 7, characterized in that, Fit the target model coordinate points into a polygon through the RANSAC algorithm.

9. A method for measuring the size of a sheet based on 3D modeling according to claim 7, characterized in that, Also included: Before fitting the target model coordinate points to obtain a fitted polygon, perform data cleaning on the target model coordinate points.

10. A sheet size measurement system based on 3D modeling, comprising a processor and a memory, the memory storing a computer program, characterized in that, The processor executes the computer program to implement a method for measuring the size of a sheet based on three-dimensional modeling according to any one of claims 1-9.

Images