Vamp track positioning and deviation rectifying method

Abstract

The invention provides a vamp track positioning and deviation rectifying method, and relates to the technical field of shoe production. According to the vamp track positioning and deviation rectifying method, the local deformation and the size difference of each vamp can be adapted, the specially-made upper and bottom bonding line track of each vamp can be accurately generated, and core technical support is provided for automation of the procedures of vamp roughing, treating agent applying, glue spraying and the like; a local deviation correction method of point-by-point local matching is adopted, so that the local deviation between a vamp template and a sample can be calibrated in a targeted manner, the positioning precision of an upper and sole bonding line track is effectively improved, and the consistency and stability of automatic processing are guaranteed; on the basis of completing local deviation correction, the generated trajectory is smoothed, and the trajectory points are projected to the vamp point cloud, so that the problem of overlarge trajectory fluctuation is avoided, and the smoothness and the accuracy of the execution process of the automatic equipment are further improved.

Description

Technical Field

[0001] This invention relates to the field of shoe manufacturing technology, and more specifically, to a method for positioning and correcting the trajectory of a shoe upper. Background Technology

[0002] The production process in the shoe manufacturing industry is mainly divided into the cutting and sewing section, the forming section, and the packaging section. The forming section is the key link in bonding the sole and the upper. The upper processing process in this section is as follows: feeding, roughing, applying treatment agent, passing through the treatment agent oven, applying glue, passing through the glue oven, and attaching the sole. In order to promote the industrial upgrading of the shoe manufacturing industry and reduce labor input, the roughing, glue spraying, and treatment agent application processes of the upper urgently need to be automated. The core prerequisite for automation is to automatically generate the bonding line trajectory of the upper and sole in the upper process. The uppers are mostly made of flexible materials, and the preceding processes such as cutting and sewing are mostly done manually. This results in certain local deformations and size differences in each upper. Although these differences are within tolerance and do not affect the final shoe quality, it is impossible to carry out automated processing of the uppers using a fixed trajectory. Currently, the industry primarily uses 3D scanning to obtain the 3D point cloud of the entire shoe upper surface, then creates a 3D template for the upper, calculates the difference between each shoe upper and the template point cloud in real time, and adjusts the template's upper and sole bonding lines based on this difference. The adjusted trajectory is then sent to a six-axis robot for execution. However, existing technologies lack adaptability to handle local deviations in the shoe upper, making it difficult to accurately generate customized upper and sole bonding line trajectories for each shoe upper, thus affecting the processing accuracy of automated processes. Therefore, we propose an improvement: a shoe upper trajectory positioning and correction method. Summary of the Invention

[0003] This invention provides a method for positioning and correcting the trajectory of a shoe upper, including: S1. Global Registration: Using the classic ICP algorithm, obtain the rotation and translation matrix for registration and alignment between the sample point cloud Sample3D and the template point cloud Model3D. Using this transformation relationship, the sample point cloud Sample3D is transformed to the template point cloud location, denoted as STM3D; S2. Local Registration: For each point in the MLine3D point set of the template bottom bonding line, using this point as the center point of a cuboid, and taking the line connecting the current point to the next point as the main direction, take the length, width, and height to form a cuboid region. Select the set of points in the template point cloud that are surrounded by the cuboid region to form a new local 3D point cloud. Similarly, from Select the set of points enclosed by the cuboid region to form a new local 3D point cloud. ; For point clouds And point cloud Several additional point sets were added; Repeat the operation to obtain the result. The updated bottom adhesive line point set ; S3, Trajectory Smoothing: Smooth the updated upper and sole bonding line and project it onto the shoe upper point cloud to obtain the final upper and sole bonding line trajectory.

[0004] As a preferred technical solution in this application, the input data includes: Template 3D point cloud That is, a set of several three-dimensional coordinate points: ; Template bottom adhesive line point set And the point set is ordered; Sample 3D point cloud, i.e., a set of several 3D coordinate points: .

[0005] As a preferred technical solution of this application, the output data is: the point set of the SLine3D adhesive line of the sample's bottom. .

[0006] As a preferred technical solution of this application, in S2, the length, width and height are 20, 80 and 80 respectively.

[0007] As a preferred technical solution of this application, in S2, the method for obtaining several point sets includes: taking two faces of a cuboid perpendicular to the main direction, obtaining point sets of the two faces by sampling, and then adding them to two local point clouds to form a template local point cloud. and sample local point cloud .

[0008] As a preferred technical solution of this application, the method for obtaining several point sets further includes: using the classic ICP algorithm to obtain the local point cloud of the template. To the local point cloud of the sample Registration and alignment rotation and translation matrices Using this transformation relationship, the current point of the template bottom adhesive line is transformed to obtain... The updated bottom adhesive line points.

[0009] As a preferred technical solution of this application, S3 specifically includes: updating the adhesive line of the upper and lower part. point set The coordinate system is reconstructed; specifically, a two-dimensional coordinate system is constructed, where the Y-axis represents the difference between the updated Z-value of each point on the adhesive line and the Z-value of the template point, and the X-axis represents the cumulative distance between two points on the adhesive line. As a reference point ( ),calculate ,( ), and transform each point to the new coordinate system according to the rules.

[0010] As a preferred technical solution of this application, S3 further includes: fitting a univariate 11th-degree polynomial equation to obtain a fitting function, and then using the X values ​​at each point to obtain an updated Y value, i.e., the value that each point should be adjusted. The adhesive line on the bottom of the template point set Each point, Update its Z value to become .

[0011] As a preferred technical solution of this application, S3 further includes: performing edge-fitting operation again, and calculating the updated points and the corresponding local 3D point cloud. The distance between each point in the local 3D point cloud is calculated. The point with the smallest median distance.

[0012] As a preferred technical solution in this application, S3 further includes: for the final The bottom adhesive line Then use rotation and translation matrices inverse matrix Adhesive lines on the bottom Convert to This generates the final sample bottom adhesive line.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: In the scheme of this application: 1. This application proposes a shoe upper trajectory positioning and correction method, which can adapt to the local deformation and size difference of each shoe upper and accurately generate a special upper and sole bonding line trajectory for each shoe upper, providing core technical support for the automation of shoe upper roughening, application of treatment agents, spraying glue and other processes; 2. This application adopts a point-by-point local matching local correction method, which can specifically calibrate the local deviation between the shoe upper template and the sample, effectively improve the positioning accuracy of the upper and sole bonding line trajectory, and ensure the consistency and stability of automated processing; 3. Based on completing local correction, this application smooths the generated trajectory and projects the trajectory points onto the shoe surface point cloud, avoiding the problem of excessive trajectory fluctuations and further improving the smoothness and accuracy of the automated equipment's execution process. Attached Figure Description

[0014] Figure 1 A flowchart of the shoe upper trajectory positioning and correction method provided in this application; Figure 2A schematic diagram of the two-dimensional coordinate system provided in this application; Figure 3 The template point cloud Model3D and template bottom adhesive line MLine3D provided in this application are schematic diagrams. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that, unless otherwise specified, the embodiments and features and technical solutions in the present invention can be combined with each other.

[0017] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0018] For an example, please refer to... Figures 1-3 A method for locating and correcting the trajectory of a shoe upper, consisting of three steps: global registration, local matching, and trajectory smoothing. The input data includes: a template 3D point cloud. That is, a set of several three-dimensional coordinate points: ; Template bottom adhesive line point set Furthermore, the point set is sequential; the sample 3D point cloud That is, a set of several three-dimensional coordinate points: .

[0019] The output data is: the point set of the SLine3D adhesive line of the sample's bottom. ; S1. Global Registration: Using the classic ICP algorithm, obtain the rotation and translation matrix for registration and alignment between the sample point cloud Sample3D and the template point cloud Model3D. Using this transformation relationship, the sample point cloud Sample3D is transformed to the template point cloud location, denoted as STM3D; S2. Local registration: Since the preceding processes of shoe upper are all done manually, and the shoe upper lasting operation is also done manually, and the shoe upper is a flexible material, there are local deviations between the shoe upper template and the shoe upper sample. In order to calibrate the local deviations, this application proposes a local registration method. Adhesive lines on the bottom of the template For each point in the point set, take that point as the center of a cuboid, and using the line connecting the current point to the next point as the main direction (length direction), take a cuboid region with a length, width, and height of 20, 80, and 80 respectively. Select the set of points in the template point cloud that are enclosed by the cuboid region to form a new local 3D point cloud. Similarly, from Select the set of points enclosed by the cuboid region to form a new local 3D point cloud. ; At this point, if the two sets of point clouds are directly registered in 3D, the registration result cannot be controlled, and deviations may occur in the principal direction (the direction of the line connecting the current point to the next point), which is unnecessary; therefore, this application is for point clouds And point cloud Several additional point sets are added. The methods for obtaining these point sets include: taking two faces of the cuboid perpendicular to the main direction, obtaining point sets from these two faces through sampling, and then adding them to two local point clouds to form a template local point cloud. and sample local point cloud The classic ICP algorithm is used to obtain the local point cloud of the template. To the local point cloud of the sample Registration and alignment rotation and translation matrices Using this transformation relationship, the current point of the template bottom adhesive line is transformed to obtain... The updated bottom adhesive line points; Repeat the operation to obtain the result. The updated bottom adhesive line point set ; S3. Track Smoothing: The updated upper and sole bonding line is smoothed and projected onto the shoe upper point cloud to obtain the final upper and sole bonding line trajectory. On the one hand, due to the error in the accuracy of registration, the adjustment range of each point is different, causing the originally smooth upper and sole bonding line to become highly volatile. On the other hand, the updated points may not be on the shoe upper point cloud. Therefore, this step is to smooth the upper and sole bonding line before edge bonding (projecting the points on the upper and sole bonding line onto the shoe upper point cloud). Specifically, this includes: updating the adhesive lines on the upper and lower parts. point set The coordinate system is reconstructed; specifically, a two-dimensional coordinate system is constructed, where the Y-axis represents the difference between the updated Z-value of each point on the adhesive line and the Z-value of the template point, and the X-axis represents the cumulative distance between two points on the adhesive line. As a reference point ( ),calculate ,( According to the rules, each point is transformed to the new coordinate system, that is, as follows: Figure 2 As shown; A univariate 11th-degree polynomial equation is used for fitting to obtain the fitted function. Then, using the X values ​​at each point, the updated Y value is obtained, which represents the adjustment that each point should make. The adhesive line on the bottom of the template point set Each point, Update its Z value to become ; Then perform the edge-fitting operation to calculate the updated points and their corresponding local 3D point clouds. The distance between each point in the local 3D point cloud is calculated. The point with the smallest median distance; For the final The bottom adhesive line Then use rotation and translation matrices inverse matrix Adhesive lines on the bottom Convert to This generates the final sample bottom adhesive line, i.e. Figure 3 As shown.

[0020] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0021] Obviously, the embodiments described above are merely some embodiments of the present invention, not all embodiments. The accompanying drawings show preferred embodiments of the present invention, but do not limit the patent scope of the present invention. The present invention can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the patent protection scope of this invention.

Claims

1. A method for locating and correcting the trajectory of a shoe upper, characterized in that, include: S1. Global Registration: Using the classic ICP algorithm, obtain the rotation and translation matrix for registration and alignment between the sample point cloud Sample3D and the template point cloud Model3D. Using this transformation relationship, the sample point cloud Sample3D is transformed to the template point cloud location, denoted as STM3D; S2. Local Registration: For each point in the MLine3D point set of the template bottom bonding line, using this point as the center point of a cuboid, and taking the line connecting the current point to the next point as the main direction, take the length, width, and height to form a cuboid region. Select the set of points in the template point cloud that are surrounded by the cuboid region to form a new local 3D point cloud. Similarly, from Select the set of points enclosed by the cuboid region to form a new local 3D point cloud. ; For point clouds And point cloud Several additional point sets were added; Repeat the operation to obtain the result. The updated bottom adhesive line point set ; S3, Trajectory Smoothing: Smooth the updated upper and sole bonding line and project it onto the shoe upper point cloud to obtain the final upper and sole bonding line trajectory.

2. The shoe upper trajectory positioning and correction method according to claim 1, characterized in that, The input data includes: Template 3D point cloud That is, a set of several three-dimensional coordinate points: ; Template bottom adhesive line point set And the point set is ordered; Sample 3D point cloud, i.e., a set of several 3D coordinate points: .

3. The shoe upper trajectory positioning and correction method according to claim 2, characterized in that, The output data is: the point set of the SLine3D adhesive line of the sample's bottom. .

4. The shoe upper trajectory positioning and correction method according to claim 1, characterized in that, In S2, the length, width, and height are 20, 80, and 80 respectively.

5. The shoe upper trajectory positioning and correction method according to claim 1, characterized in that, In S2, the method for obtaining several point sets includes: taking two faces of a cuboid perpendicular to the main direction, obtaining point sets from the two faces through sampling, and then adding them to two local point clouds to form a template local point cloud. and sample local point cloud .

6. The shoe upper trajectory positioning and correction method according to claim 5, characterized in that, Methods for obtaining several point sets also include: using the classic ICP algorithm to obtain the local point cloud of the template. To the local point cloud of the sample Registration and alignment rotation and translation matrices Using this transformation relationship, the current point of the template bottom adhesive line is transformed to obtain... The updated bottom adhesive line points.

7. The shoe upper trajectory positioning and correction method according to claim 1, characterized in that, S3 specifically includes: the updated backing and adhesive lines. point set The coordinate system is reconstructed; specifically, a two-dimensional coordinate system is constructed, where the Y-axis represents the difference between the updated Z-value of each point on the adhesive line and the Z-value of the template point, and the X-axis represents the cumulative distance between two points on the adhesive line. As a reference point ( ),calculate ,( ), and transform each point to the new coordinate system according to the rules.

8. The shoe upper trajectory positioning and correction method according to claim 7, characterized in that, S3 also includes: fitting the equation using a univariate 11th-degree polynomial to obtain a fitted function, and then using the X values ​​at each point to obtain an updated Y value, i.e., the value that each point should be adjusted. The adhesive line on the bottom of the template point set Each point, Update its Z value to become .

9. The shoe upper trajectory positioning and correction method according to claim 8, characterized in that, S3 also includes: performing edge-fitting operations again, calculating the updated points and their corresponding local 3D point clouds. The distance between each point in the local 3D point cloud is calculated. The point with the smallest median distance.

10. The shoe upper trajectory positioning and correction method according to claim 9, characterized in that, S3 also includes: for the final The bottom adhesive line Then use rotation and translation matrices inverse matrix Adhesive lines on the bottom Convert to This generates the final sample bottom adhesive line.

Images