High-precision polishing line extraction method for shoe upper polishing equipment

Abstract

The present application relates to the technical field of shoe upper processing, more specifically, it relates to a high-precision polishing line extraction method for shoe upper polishing equipment, on the basis of obtaining imaging photos of each orientation of the shoe upper by using a 3D scanning camera to scan and photograph the shoe upper in all directions, the polishing area and the non-polishing area of the shoe upper are divided by color in advance, the polishing line is constructed, the identification area of the polishing line is established, the polishing line is identified by using the gradient difference of the gray scale image, and then the polishing line is mapped on the 3D point cloud of the template shoe upper to obtain detailed point cloud data of the polishing line, the shoe upper curvature of each polishing point of the template shoe upper is matched, the polishing posture of the sanding wheel is calculated, the high-precision extraction and identification of the polishing line are realized, the accuracy and stability of the polishing process are ensured, and the production efficiency of the shoe upper is improved.

Description

Technical Field

[0001] This invention relates to the field of shoe upper processing technology, and more specifically, to a method for extracting high-precision grinding lines for shoe upper grinding equipment. Background Technology

[0002] In footwear manufacturing, the finishing process of the upper is crucial, directly affecting the appearance and comfort of the shoe. However, traditional hand-finishing methods have a series of problems, including low efficiency and poor precision, making it difficult to meet the demands and standards of modern production. With the advancement of technology, the development of automation technology has provided new possibilities for solving this problem.

[0003] With the help of advanced 3D scanning and image processing technologies, we can achieve efficient and accurate automated polishing of shoe uppers. This technology can not only significantly improve production efficiency but also ensure product consistency and quality. However, to achieve this goal, a key challenge needs to be overcome: how to accurately extract polishing lines from 3D scan data and effectively apply them to polishing equipment to ensure the accuracy and stability of the polishing process. Summary of the Invention

[0004] To address the shortcomings of the existing technology, the purpose of this invention is to provide a high-precision grinding line extraction method for shoe upper grinding equipment, which has the advantages of ensuring the accuracy and stability of the grinding process and improving the production efficiency of shoe uppers.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution: a method for extracting high-precision grinding lines for shoe upper grinding equipment, the method comprising:

[0006] S1: Establish identification areas, divide the polished and unpolished areas of the shoe upper into regions using color, and construct polishing lines;

[0007] S2: Image capture. The 3D scanning camera scans the shoe upper from all angles to obtain images from various perspectives.

[0008] S3: Obtain the point cloud data of the polishing line, identify the polishing line by using the gradient difference of the grayscale image of the imaging photo, and then map the polishing line onto the 3D point cloud of the template shoe upper to obtain the detailed point cloud data of the polishing line.

[0009] S4: Correct the polishing posture. For each polishing point, match the curvature of the shoe upper at each polishing point on the template shoe upper, and calculate the polishing posture of the correct polishing wheel.

[0010] Preferably, in the preprocessing of the image, the interference areas on the non-polished area are manually identified, the interference areas are marked, and the interference areas are further distinguished by deepening the color.

[0011] Preferably, the taking picture process further comprises a graphical user interface for displaying the imaging photo of the completed polishing line, the imaging photo identifies the polishing line at a set display threshold, and the set display threshold can be automatically adjusted or manually intervened according to the identification of the polishing line until the polishing line is accurately identified.

[0012] Preferably, based on the obtained polishing line point cloud data, a 3D view of the polishing line is displayed through the graphical user interface, and the interference noise points on the polishing line are determined and corrected by human.

[0013] Preferably, after obtaining the detailed point cloud data of the polishing line, the polishing line points are sorted counterclockwise and down-sampled at equal distances to ensure that the polishing points are uniformly distributed in the 3D space.

[0014] Preferably, the obtained polishing line point cloud data and the obtained correction polishing posture are data-archived to establish an operation standard, and the operation standard is used to directly call the polishing line point cloud data and the correction polishing posture in the next polishing line identification.

[0015] In summary, the present application has the beneficial effects: on the basis of scanning and photographing the upper in all directions by the 3D scanning camera to obtain imaging photos of the upper in all directions, the polishing area and the non-polishing area of the upper are divided by color in advance, the polishing line is constructed, the identification area of the polishing line is established, the polishing line is identified by using the gray scale gradient difference of the imaging photo, the polishing line is mapped on the 3D point cloud of the template upper, the detailed point cloud data of the polishing line is obtained, the shoe upper curvature of each polishing point of the template upper is matched for each polishing point, the polishing posture of the sanding wheel is calculated, and high-precision extraction and identification of the polishing line are realized, the accuracy and stability of the polishing process are ensured, and the production efficiency of the upper is improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a step schematic diagram of an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the technical problems to be solved by the present application, the technical solutions and beneficial effects more clearly understood, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0018] It should be noted that when a component is referred to as "fixed to" or "disposed on" another component, it can be directly on the other component or indirectly on the other component. When a component is referred to as "connected to" another component, it can be directly or indirectly connected to the other component.

[0019] It should be understood that the terms "length", "width", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0020] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0021] A high-precision polishing line extraction method for a shoe upper polishing device, referring to Figure 1 , the method comprises:

[0022] S1: Establish an identification area, divide the polishing area and the non-polishing area with color, and construct a polishing line;

[0023] S2: Take a picture, scan and take pictures of the shoe upper in all directions with a 3D scanning camera, and obtain imaging photos of each direction;

[0024] S3: Obtain polishing line point cloud data, identify the polishing line by using the gradient difference of the gray scale image, and map the polishing line on the 3D point cloud of the template shoe upper to obtain detailed point cloud data of the polishing line.

[0025] S4: Correct the polishing posture, align the shoe upper curvature rate at each polishing point of the template shoe upper, and calculate the polishing posture of the grinding wheel.

[0026] On the basis of scanning and taking pictures of the shoe upper in all directions by a 3D scanning camera, obtaining imaging photos of each direction of the shoe upper, dividing the polishing area and the non-polishing area with color in advance, constructing a polishing line, establishing an identification area of the polishing line, identifying the polishing line by using the gradient difference of the imaging photo, and mapping the polishing line on the 3D point cloud of the template shoe upper to obtain detailed point cloud data of the polishing line, aligning the shoe upper curvature rate at each polishing point of the template shoe upper, and calculating the polishing posture of the grinding wheel, the high-precision extraction and identification of the polishing line are realized, the accuracy and stability of the polishing process are ensured, and the production efficiency of the shoe upper is improved.

[0027] The 3D point cloud of the template shoe upper is obtained in the following way:

[0028] I. Establish a 3D model database of template uppers, directly call the template upper in the 3D model database, map the polishing line on the 3D point cloud of the template upper, and then obtain the detailed point cloud data of the polishing line;

[0029] II. Scan the upper by a 3D scanning camera to establish a 3D model of the current upper. After distinguishing the polishing line, map the polishing line on the 3D point cloud of the template upper, and then obtain the detailed point cloud data of the polishing line.

[0030] Self-adaptive online polishing trajectory prediction of the sanding wheel:

[0031] Step one: select a starting point A, an ending point B and a normal vector N along the polishing trajectory P , construct a directed feed plane along the length and width directions of the upper. Among them, points A and B are the starting point and ending point of the pre-planned polishing path respectively, and the normal vector N P is the normal of the plane passing through points A and B. The plane feed direction can be set according to the machining conditions of the workpiece to be machined surface.

[0032] The tool center point TCP is set as the fixed point of the sanding wheel end. TCP changes its pose with the floating of the industrial robot and the polishing spindle.

[0033] We set the origin of the sanding wheel coordinate system as TCP, and the z-axis direction of the sanding wheel coordinate system is consistent with the axis direction of the polishing spindle.

[0034] The positive direction of the z-axis of the sanding wheel coordinate system represents the direction of the sanding wheel approaching the upper.

[0035] When the robot system polishes, the reaction force Fc of the upper on the sanding wheel is decomposed into the x-axis, y-axis and z-axis of the sanding wheel coordinate system. These forces are measured by a six-axis force sensor installed on the flange of the industrial robot. By adjusting the size of the reaction force of the upper on the sanding wheel, the adaptive adjustment of the sanding wheel to the curved upper is realized.

[0036] Specifically, the imaging photo is preprocessed, the interference area on the non-polishing area is determined by human judgment, the interference area is labeled, and the interference area is further distinguished by deepening the color division.

[0037] This embodiment adopts a 3D laser camera module, which moves the 3D laser camera module in a fixed direction to take photos in four directions of the upper, i.e. front, back, left and right. After the imaging photo is taken, it is viewed by a person to determine the interference area on the non-polishing area that can interfere with the polishing line recognition. The interference area is labeled and distinguished by deepening the color division, further distinguishing the non-polishing area and the polishing area, and deepening the recognition degree of the polishing line.

[0038] Specifically, the taking process further includes a graphical user interface for displaying the imaging photo of the taking process, the imaging photo identifies the polishing line at a set display threshold, and the set display threshold can be automatically adjusted or manually intervened according to the identification of the polishing line until the polishing line is accurately identified.

[0039] By directly displaying the imaging photo taken during the taking process through the graphical user interface, the 3D laser camera module of the embodiment is electrically connected to the graphical user interface through the electric control host, realizing information interaction between the 3D laser camera module and the graphical user interface.

[0040] On this basis, the imaging photo is identified at a set display threshold, and the set display threshold can be automatically adjusted or manually intervened according to the identification of the polishing line until the polishing line is accurately identified.

[0041] Specifically, based on the obtained polishing line point cloud data, the 3D view of the polishing line is displayed through the graphical user interface, the interference noise points on the polishing line are determined by human judgment, and are corrected and removed.

[0042] The extracted polishing line is displayed in the 3D view. If there are interference noise points, the user can manually delete these unnecessary data points to purify the polishing line data.

[0043] Specifically, after obtaining the detailed point cloud data of the polishing line, the polishing line points are sorted counterclockwise, and equal-interval downsampling is performed to ensure uniform distribution of the polishing points in 3D space.

[0044] Counterclockwise sorting:

[0045] First, ensure that the polishing line points are arranged in a counterclockwise direction. This can be achieved by calculating the polar angle (or azimuth angle) of each point relative to a reference point. Then sort these polar angles to get the point sequence in counterclockwise direction.

[0046] Equal-interval downsampling:

[0047] Equal-interval downsampling can ensure uniform distribution of the polishing points in 3D space. The specific steps are as follows:

[0048] Calculate the distance between adjacent polishing line points.

[0049] Determine a suitable interval distance, for example, set a fixed distance threshold.

[0050] From the counterclockwise sorted polishing line point sequence, select the first point as the starting point, then traverse the sequence, and calculate the distance between the current point and the last selected point.

[0051] If the distance exceeds the set interval distance, the current point is added to the polishing point sequence and taken as a new starting point.

[0052] Repeat the above steps until all polishing line points are traversed.

[0053] The final polishing point sequence is the result of equal-distance downsampling.

[0054] Specifically, the obtained polishing line point cloud data and the obtained corrected polishing posture are data-archived to establish operation standards. According to the operation standards, the obtained polishing line point cloud data and the corrected polishing posture are directly called in the next polishing line identification.

[0055] Data archiving:

[0056] The obtained polishing line point cloud data and the corrected polishing posture are archived. This may involve saving the data into a file, ensuring that the file name and storage path are easily accessible and identifiable.

[0057] Establishing standardized storage format:

[0058] Ensure that the polishing line point cloud data and the corrected polishing posture adopt a standardized storage format, so that they can be conveniently called in the next use. This can be a common data format such as PLY, OBJ, or a custom data format to meet specific needs.

[0059] Recording metadata:

[0060] Record metadata information about the data in the archive, such as collection date, collection device, polishing parameters, etc. These information helps to understand the source and background of the data in subsequent use.

[0061] Establishing a calling program:

[0062] Develop or configure a program for directly calling the archived polishing line point cloud data and the corrected polishing posture in the next polishing line identification. This program can be a custom script, a software tool, or integrated into the control system of the polishing device.

[0063] Verification and update:

[0064] Before using the calling program, ensure that the archived data is verified to ensure the integrity and accuracy of the data. If the archived data or standards need to be updated, update them in a timely manner.

[0065] By establishing such operation standards, you can conveniently call the polishing line point cloud data and the corrected polishing posture in the next polishing line identification, thereby improving production efficiency and ensuring the consistency and quality of polishing.

[0066] The above examples are only explanations of the present application, which are not limitations of the present application, and those skilled in the art can make modifications to the present examples without creative contributions after reading the present specification, but as long as the modifications are within the scope of the claims of the present application, they are protected by the patent law.

Claims

1. A method for extracting high-precision grinding lines using shoe upper grinding equipment, characterized in that: The method includes: S1: Establish identification areas, divide the polished and unpolished areas of the shoe upper into regions using color, and construct polishing lines; S2: Image capture. The 3D scanning camera scans the shoe upper from all angles to obtain images from various perspectives. S3: Obtain the point cloud data of the polishing line, identify the polishing line by using the gradient difference of the grayscale image of the imaging photo, and then map the polishing line onto the 3D point cloud of the template shoe upper to obtain the detailed point cloud data of the polishing line. S4: Correct the polishing posture. For each polishing point, match the curvature of the shoe upper at each polishing point on the template shoe upper, and calculate the polishing posture of the correct polishing wheel. After obtaining detailed point cloud data of the grinding line, the grinding line points are sorted counterclockwise and downsampled at equal intervals to ensure that the grinding points are evenly distributed in 3D space. The preprocessing of the image involves manually identifying interference areas in the non-polished areas, calibrating these interference areas, and further distinguishing and deepening the colors of these interference areas.

2. The method for extracting high-precision grinding lines using shoe upper grinding equipment according to claim 1, characterized in that: During the film retrieval process, a graphical user interface is also included to display the image of the film retrieval process. The image of the film identifies the grinding line under a set display threshold, and the set display threshold can be automatically adjusted or manually intervened according to the recognition of the grinding line until the grinding line is accurately identified.

3. The method for extracting high-precision grinding lines in a shoe upper grinding equipment according to claim 2, characterized in that: base The point cloud data of the acquired grinding line is used to display a 3D view of the grinding line through the graphical user interface. Interference noise points on the grinding line are identified and corrected or removed by the user.

4. The method for extracting high-precision grinding lines in a shoe upper grinding equipment according to claim 1, characterized in that: The acquired grinding line point cloud data and the acquired corrected grinding posture are archived to establish operating standards. According to the operating standards, the grinding line point cloud data and the corrected grinding posture are directly retrieved in the next grinding line recognition.

Images