A control method for an automatic milling device for tire tread blocks based on binocular 3D vision

Abstract

This invention discloses a control method for an automatic tire tread block milling device based on binocular 3D vision in the field of machine vision technology. The method includes: a camera acquiring an image of a calibration plate and recording the machine tool position; calibrating the vision system parameters and the rotation axis center; after fixing the tread block, the machine tool moves it to the image capture position, the camera captures an image to identify the hole pose, the machine tool then moves the milling cutter to align the hole and records the position; the tread block is fixed and moved again to capture an image, the hole center coordinates are located, and the binocular matching correction is used to obtain the 3D coordinates, and the initial pose is fitted and corrected; the groove centerline is located, a point cloud is constructed, projection points are selected, the hole depth is corrected, the groove position is calculated, and finally, the processing position is calculated to process the tread block. This invention, through calibration, teaching, positioning, chamfering, and milling, ultimately completes a four-axis robot vision-guided automatic milling task with an overall accuracy requirement of over 0.3mm.

Description

Technical Field

[0001] This invention relates to the field of machine vision technology, and in particular to a machine vision-guided precision machining method. Background Technology

[0002] Grooving the back holes of tire mold tread blocks is a crucial step in tire manufacturing. These back holes not only affect the tire's bearing performance but also significantly impact its balance, wear resistance, and other performance indicators. Due to the irregular shrinkage of aluminum-magnesium tread blocks during casting and the inherent errors in the drilling positions, CNC machining of the back hole air passages based on the model is not feasible. Currently, the back hole air passages of aluminum-magnesium tread blocks are grooved manually. To address the low efficiency of manual back hole air passage grooving, a vision camera is used to measure the back hole positions and guide a four-axis machine tool to perform the grooving. Summary of the Invention

[0003] In response to the urgent need for automatic milling equipment for tire tread blocks, this invention provides an automatic milling device and control method for tire tread blocks based on binocular 3D vision. Through calibration, teaching, positioning, chamfering, and milling, the device ultimately completes the automatic milling task guided by the vision of a four-axis robot with an overall accuracy requirement of more than 0.3mm.

[0004] The objective of this invention is achieved as follows: a control method for an automatic milling device for tire tread blocks based on binocular 3D vision, comprising two stages: calibration and teaching, and positioning and machining.

[0005] Phase 1) Calibration and Demonstration:

[0006] Step S1) First, fix the calibration plate on the clamping platform, control the movement of the four-axis machine tool, and use the camera to capture images of the calibration plate in different poses in the machine tool coordinate system, while recording the machine tool position.

[0007] Step S2) Calibrate the vision system parameters and rotation axis center;

[0008] Step S3) Place the pattern block on the clamping mechanism and fix it. Control the machine tool to move the pattern block to the shooting position and record the machine tool position at this time. At the same time, the camera takes a picture to identify the pose of the hole closest to the center of the pattern block and records it. Control the machine tool to align the end of the milling cutter with the hole and record the machine tool position.

[0009] Phase 2) Positioning and Processing Phase:

[0010] Step S4) Place the patterned block onto the clamping mechanism and fix it, move it to the shooting position, and control the left and right cameras to capture images simultaneously;

[0011] Step S5) Locate the coordinates of the center of all holes in the two images, perform binocular matching and correction on the hole coordinates in the two images, and calculate the 3D coordinates of all holes;

[0012] Step S6) Fit the initial pose of the patterned block according to the 3D coordinates of all holes and perform correction;

[0013] Step S7) Locate the center line of the groove, construct the point cloud on the back of the patterned block by combining the pose and radius information of the patterned block, calculate the coordinates of the projection points of the point cloud in the image, filter out the projection points closest to the center line of the groove, and obtain the corresponding point cloud.

[0014] Step S8) Calculate the position of the groove corresponding to all holes based on the depth information of the holes on the back of the patterned block corrected by the point cloud;

[0015] Step S9) Calculate the position that the machine tool needs to reach when chamfering and milling groove, and process the pattern block.

[0016] Further, step S1 specifically involves: fixing the calibration plate on the clamping platform to ensure that the calibration plate and the platform are rigidly connected; controlling the machine tool to move the calibration plate multiple times at the same angle within the camera's field of view, acquiring 20 sets of calibration plate images and corresponding machine tool positions; controlling the machine tool to rotate the calibration plate multiple times at the same position within the camera's field of view, acquiring 20 sets of calibration plate images and corresponding machine tool positions.

[0017] Furthermore, step S2 specifically involves calibrating the 40 sets of calibration board images acquired in step S1 to obtain the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the pose relationship of the left camera coordinate system in the right camera coordinate system. Where subscript C1 represents the left camera and superscript C2 represents the right camera; in calibration step S1, the 20 sets of images acquired by translation are compared with the corresponding machine tool positions to obtain the position of the left camera coordinate system in the machine tool coordinate system. The superscript B represents the machine tool coordinate system; in calibration step S1, 20 sets of images acquired through multiple rotations are compared with the corresponding machine tool positions to obtain the pose of the rotation axis in the machine tool coordinate system, and the coordinate system of the rotation center is obtained. The origin and direction of this coordinate system are obtained through calibration.

[0018] Further, step S5 specifically involves: first, using a deep learning object detection method to roughly locate the approximate regions of all holes; then, using a scalable shape template matching method to precisely locate the coordinates of all holes within these regions; next, locating the hole closest to the center of the patterned block, fitting the point cloud of the entire back of the patterned block using the known radius, back-projecting all 3D points onto the image coordinate system, using the precise localization result of the left camera image as a reference, finding the corresponding hole in the right camera image, and creating an NCC template based on the hole in the left image, finding the corresponding hole in the right image, correcting the coordinates of the right image, and finally obtaining the 3D coordinates of all holes in the stereo system. , where the superscript n is the hole number.

[0019] Furthermore, step S6 specifically involves: firstly, fitting a straight cylinder based on the point cloud formed by all the holes to obtain the coordinate system of the patterned block. Its origin is at the highest point of the fitted cylinder's side surface, the X-axis is parallel to the cylinder's axis, and the Z-axis points to the cylinder's geometric center. Then, the entire patterned block area is located and divided into 60 rectangular regions. The 3D coordinates of the holes in each region are projected onto the cylinder's bottom surface for circle fitting. The highest point of this circle in the patterned block coordinate system is obtained and projected back into 3D space. Finally, based on the 60 highest points, the highest generatrix in the initial patterned block coordinate system is fitted. The direction of this generatrix is ​​then used to adjust the patterned block coordinate system. Perform corrections.

[0020] Further, step S7 specifically involves: combining target detection with traditional image processing methods to obtain the center line of the groove; based on the pattern block coordinate system obtained in step S6 and the known radius information, establishing a point cloud set on the back of the pattern block; calculating the projection coordinate set of the point cloud in the left image; finding the line connecting the projection point closest to the center line of the groove; and the point cloud coordinates corresponding to the projection point are the point cloud coordinates corresponding to the center line of the groove.

[0021] Furthermore, step S8 specifically involves: correcting the Z-axis coordinates of the 3D coordinates of all back holes obtained in step S5 based on the point cloud model established in step S7; firstly, finding the coordinates closest to the back hole in the 2D projection coordinate set of the point cloud in the left image, and then using the Z-axis coordinates of the point cloud corresponding to these coordinates to replace the back hole coordinates. The Z-axis coordinates are calculated; the point on the trench centerline point cloud closest to the 3D coordinates of the back hole is calculated to obtain the position of the trench corresponding to all holes. .

[0022] Furthermore, step S9 specifically involves: firstly, based on... Backhole coordinates in camera coordinate system Transform to the machine tool coordinate system, that is: ,in This only includes the 3D coordinate information of the holes. Additionally, it's necessary to calculate the angle of rotation of the machine tool's A-axis when all holes reach their highest point after rotating around the machine tool's X-axis. This angle is the rotation axis coordinate system. In the YZ plane, calculate the angle between the line connecting the center of rotation and the hole and the Z-axis, then calculate the rotation of the hole around the axis of rotation. The coordinates after the angle give the pose of the rotated hole. Similarly, the pose of the groove corresponding to the rotated hole can be obtained. Based on the photo-taking pose recorded in step S3 The position of the milling cutter aligned with the hole closest to the center of the pattern block. The position of the patterned block closest to the center hole ; Calculate the position the machine tool needs to reach during chamfering. ,in:

[0023] ,

[0024] ,

[0025] Similarly, the position that the machine tool needs to reach when milling grooves can be obtained.

[0026] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention can identify all the positional information required for processing with a single photograph, the visual processing time is greatly shortened compared with laser scanning, and it can realize the automatic processing of molds with irregular shrinkage during the casting process, with high processing accuracy, fast speed and good consistency; before this, only manual milling tasks could be performed, which was inefficient and had poor consistency. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0028] Figure 1 This is a flowchart of the tire mold processing in this invention.

[0029] Figure 2 This is a partial image of the calibration plate after translation and rotation in this invention.

[0030] Figure 3 This is a diagram illustrating the binocular back projection effect in this invention.

[0031] Figure 4 This is a schematic diagram of the rotation center coordinate system in this invention.

[0032] Figure 5 This is a schematic diagram of the point cloud projection effect in this invention.

[0033] Figure 6 This is a schematic diagram illustrating the local hole positioning and correction effect in this invention.

[0034] Figure 7 This is a schematic diagram of the side surface of a cylinder fitted with point cloud in this invention.

[0035] Figure 8 This is a schematic diagram of the rectangular region division in this invention.

[0036] Figure 9 This is a schematic diagram of the highest point fitting in this invention.

[0037] Figure 10 This is a schematic diagram of busbar positioning in this invention.

[0038] Figure 11 This is a schematic diagram of the trench positioning effect in this invention.

[0039] Figure 12 This is a schematic diagram illustrating the errors before and after local point cloud correction in this invention.

[0040] Figure 13 This is a schematic diagram showing the correspondence between through holes and grooves in this invention.

[0041] Figure 14 This is a diagram showing the on-site implementation and partial chamfering effect of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0043] like Figure 1 The device and control method for automatic milling of tire tread blocks based on binocular 3D vision, shown below, include two stages: calibration and teaching, and positioning and machining (see attached diagram). Figure 1 ):

[0044] Calibration and demonstration phase:

[0045] Step S1: First, fix the calibration plate on the clamping platform, control the movement of the four-axis machine tool, and use a camera to capture images of the calibration plate in different poses in the machine tool coordinate system, while simultaneously recording the machine tool position; specifically:

[0046] The calibration plate is fixed on the clamping platform, ensuring a rigid connection between the calibration plate and the platform. The machine tool is controlled to move the calibration plate multiple times at the same angle within the camera's field of view, acquiring 20 sets of calibration plate images and corresponding machine tool positions. The machine tool is then controlled to rotate the calibration plate multiple times at the same position within the camera's field of view, acquiring 20 sets of calibration plate images and corresponding machine tool positions. The calibration plate images serve as a reference. Figure 2 .

[0047] In this step, the translation and rotation processes are calibrated separately by acquiring images, which helps to calibrate translation and rotation separately and avoid motion coupling.

[0048] Step S2: Calibrate the vision system parameters and rotation axis center; specifically:

[0049] The 40 sets of calibration board images acquired in calibration step S1 yielded the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the pose relationship of the left camera coordinate system in the right camera coordinate system.

[0050] ,

[0051] The translation unit is meters (m), the rotation unit is degrees (°), subscript C1 represents the left camera, superscript C2 represents the right camera, the back projection error is 0.133194 pixels, and the back projection effect is as follows. Figure 3 In calibration step S1, the 20 sets of images acquired through multiple translations are compared with the corresponding machine tool positions to obtain the position of the left camera coordinate system in the machine tool coordinate system.

[0052] ,

[0053] The superscript B represents the machine tool coordinate system. The average calibration error of the X-axis is 0.0131255 mm, the average calibration error of the Y-axis is 0.0165558 mm, and the average calibration error of the Z-axis is 0.0294939 mm.

[0054] In calibration step S1, 20 sets of images acquired through multiple rotations are compared with the corresponding machine tool positions to obtain the pose of the rotary axis in the machine tool coordinate system, and the coordinate system of the rotation center is obtained. The origin and direction of this coordinate system are obtained through calibration, such as... Figure 4 The transformation relationship between this coordinate system and the machine tool coordinate system is as follows:

[0055] .

[0056] This step calibrates the XYZ axes of the machine tool based on the calibration plate image and the machine tool's motion coordinate values ​​corresponding to the translation process, and calibrates the R axis of the machine tool based on the calibration plate image and the machine tool's motion coordinate values ​​corresponding to the rotation process. This greatly simplifies the calibration process and provides a foundation for subsequent high-precision calculations.

[0057] Step S3: Place the pattern block on the clamping mechanism and fix it. Control the machine tool to move the pattern block to the photo-taking position and record the machine tool position at this time. At the same time, the camera takes a picture to identify the pose of the hole closest to the center of the pattern block and records it. Control the machine tool to align the end of the milling cutter with the hole and record the machine tool position.

[0058] Positioning and processing stage:

[0059] Step S4: Place the patterned block onto the clamping mechanism and fix it in place. Move it to the shooting position and control the left and right cameras to capture images simultaneously.

[0060] Step S5: Locate the coordinates of the center of all holes in the two images, and perform binocular matching and correction on the hole coordinates in the two images to calculate the 3D coordinates of all holes; specifically: first, use a deep learning object detection method to coarsely locate the approximate area of ​​all holes, and then use a scalable shape template matching method to finely locate the accurate coordinates of all holes in these areas; then locate the hole closest to the center of the patterned block, and fit the point cloud of the entire back of the patterned block with the known radius, and backproject all 3D points onto the image coordinate system, such as... Figure 5 Using the precise localization result from the left camera image as a reference, the corresponding hole in the right camera image is located. An NCC template is then created based on the hole in the left image. The hole is then located at its corresponding position in the right image, and the coordinates of the right image are corrected. The local localization result is as follows: Figure 6 Finally, the 3D coordinates of all holes in the stereo system were obtained. , where the superscript n is the hole number.

[0061] By using deep learning to stably locate all through holes, and then using NCC matching to correct the coordinates of the holes in the right camera to make them consistent with the coordinates of the hole centers in the left camera, the accuracy of the binocular system is improved. This step achieves both the stability of hole feature extraction by deep learning and the accuracy of hole position extraction by traditional NCC matching.

[0062] Step S6: Fit the initial pose of the patterned block based on the 3D coordinates of all holes and perform correction; specifically:

[0063] First, a straight cylinder is fitted based on the point cloud formed by all the holes to obtain the coordinate system of the patterned block. Its origin is at the highest point of the fitted cylinder's lateral surface, the X-axis is parallel to the cylinder's axis, and the Z-axis points to the cylinder's geometric center, as shown below. Figure 7 Then locate the entire area containing the patterned block and divide it into 60 rectangular areas, such as... Figure 8 The 3D coordinates of the holes in each region are projected onto the bottom surface of the cylinder for circle fitting. The highest point of this circle in the pattern block coordinate system is then obtained and projected back into 3D space, such as... Figure 9 Finally, based on the 60 highest points, the highest generatrix in the initial coordinate system of the pattern block was fitted, as shown below. Figure 10 According to the direction of the generatrix, the coordinate system of the pattern block Perform corrections.

[0064] This step first obtains the pattern block coordinate system by fitting the point cloud, which is the basis for subsequent calculations and ensures the accuracy of subsequent correction and calculation steps. By combining the highest points of the circle fitting of 60 regions to perform straight line fitting, the direction of the generatrix is ​​not affected by the extraction accuracy of a single outlier center point, thus achieving the best stability.

[0065] Step S7: Locate the centerline of the groove, construct a point cloud on the back of the patterned block by combining the pose and radius information of the patterned block, calculate the coordinates of the projection points of the point cloud in the image, and select the projection points closest to the centerline of the groove to obtain the corresponding point cloud; specifically: combine target detection and traditional image processing methods to obtain the centerline of the groove, establish a point cloud set on the back of the patterned block according to the coordinate system of the patterned block obtained in step S6 and the known radius information, calculate the projection coordinate set of the point cloud in the left image, find the line connecting the projection points closest to the centerline of the groove, and the point cloud coordinates corresponding to the projection points are the point cloud coordinates corresponding to the centerline of the groove. The groove localization effect is as follows. Figure 11 .

[0066] This step combines the point cloud projection of the back hole of the overall patterned block extracted in step 5 with the groove center line obtained from image processing. This can efficiently find the groove center line closest to the force-corresponding hole and then calculate their connection. It does not require accurate segmentation of the groove position on the image, which reduces the difficulty of image recognition and improves the stability of groove positioning.

[0067] Step S8: Correct the depth information of the holes on the back of the patterned block based on the point cloud, and calculate the position of the grooves corresponding to all holes; specifically: correct the Z-axis coordinates of the 3D coordinates of all back holes obtained in Step S5 based on the point cloud model established in Step S7: first, find the coordinates closest to the back hole in the 2D projection coordinate set of the point cloud in the left image, and use the Z-axis coordinates of the point cloud corresponding to these coordinates to replace the back hole. The Z-axis coordinates, and the errors before and after local point cloud correction are as follows: Figure 12 Calculate the point on the point cloud of the trench centerline that is closest to the 3D coordinates of the back hole, and obtain the position of the trench corresponding to all holes. ,like Figure 13 .

[0068] This step, using the corrected points, can ensure the consistency of positioning accuracy for all through holes, reduce the positioning error of through holes at the edge of the mold caused by angle, and ensure the overall processing quality.

[0069] Step S9: Calculate the position the machine tool needs to reach during chamfering and milling, and machine the pattern block (see attached). Figure 14 Specifically:

[0070] Firstly, according to Backhole coordinates in camera coordinate system Transform to the machine tool coordinate system, that is: ,in This only includes the 3D coordinate information of the holes. Additionally, it's necessary to calculate the angle of rotation of the machine tool's A-axis when all holes reach their highest point after rotating around the machine tool's X-axis. This angle is the rotation axis coordinate system. In the YZ plane, calculate the angle between the line connecting the center of rotation and the hole and the Z-axis, then calculate the rotation of the hole around the axis of rotation. The coordinates after the angle give the pose of the rotated hole. Similarly, the pose of the groove corresponding to the rotated hole can be obtained. Based on the photo-taking pose recorded in step S3 The position of the milling cutter aligned with the hole closest to the center of the pattern block. The position of the patterned block closest to the center hole ; Calculate the position the machine tool needs to reach during chamfering. ,in:

[0071] ,

[0072] ,

[0073] Similarly, the position that the machine tool needs to reach when milling grooves can be obtained.

[0074] This calculation method, without changing the mechanical structure, only requires guiding the mold under the camera to take a picture once to calculate the position information of all axes needed for processing, and then performing fully automatic pattern block processing, which greatly improves processing efficiency.

[0075] The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. It should be noted that those skilled in the art can make several improvements and modifications to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. A control method for an automatic milling device for tire tread blocks based on binocular 3D vision, characterized in that, It includes two stages: calibration and teaching, and localization and processing. Phase 1) Calibration and Demonstration: Step S1) First, fix the calibration plate on the clamping platform, control the movement of the four-axis machine tool, and use the camera to capture images of the calibration plate in different poses in the machine tool coordinate system, while recording the machine tool position. Step S2) Calibrate the vision system parameters and rotation axis center; Step S3) Place the pattern block on the clamping mechanism and fix it. Control the machine tool to move the pattern block to the shooting position and record the machine tool position at this time. At the same time, the camera takes a picture to identify the pose of the hole closest to the center of the pattern block and records it. Control the machine tool to align the end of the milling cutter with the hole and record the machine tool position. Phase 2) Positioning and Processing Phase: Step S4) Place the patterned block onto the clamping mechanism and fix it, move it to the shooting position, and control the left and right cameras to capture images simultaneously; Step S5) Locate the coordinates of the center of all holes in the two images, perform binocular matching and correction on the hole coordinates in the two images, and calculate the 3D coordinates of all holes; Step S6) Fit the initial pose of the patterned block according to the 3D coordinates of all holes and perform correction; Step S7) Locate the center line of the groove, construct the point cloud on the back of the patterned block by combining the pose and radius information of the patterned block, calculate the coordinates of the projection points of the point cloud in the image, filter out the projection points closest to the center line of the groove, and obtain the corresponding point cloud. Step S8) Calculate the position of the groove corresponding to all holes based on the depth information of the holes on the back of the patterned block corrected by the point cloud; Step S9) Calculate the position that the machine tool needs to reach when chamfering and milling groove, and process the pattern block.

2. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 1, characterized in that, Step S1 is as follows: the calibration plate is fixed on the clamping platform to ensure that the calibration plate and the platform are rigidly connected; the machine tool is controlled to move the calibration plate multiple times at the same angle within the camera's field of view, and 20 sets of calibration plate images and corresponding machine tool positions are collected; the machine tool is controlled to rotate the calibration plate multiple times at the same position within the camera's field of view, and 20 sets of calibration plate images and corresponding machine tool positions are collected.

3. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 2, characterized in that, Step S2 specifically involves calibrating the 40 sets of calibration board images acquired in step S1 to obtain the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the pose relationship between the left camera coordinate system and the right camera coordinate system. ; Where subscript C1 represents the left camera and superscript C2 represents the right camera; in calibration step S1, the 20 sets of images acquired are repeatedly translated and compared with the corresponding machine tool positions to obtain the position of the left camera coordinate system in the machine tool coordinate system. The superscript B represents the machine tool coordinate system; in calibration step S1, 20 sets of images acquired through multiple rotations are compared with the corresponding machine tool positions to obtain the pose of the rotation axis in the machine tool coordinate system, and the coordinate system of the rotation center is obtained. The origin and direction of this coordinate system are obtained through calibration.

4. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 3, characterized in that, Step S5 is as follows: First, a deep learning object detection method is used to roughly locate the approximate regions of all holes. Within these regions, a scalable shape template matching method is used to precisely locate the coordinates of all holes. Then, the hole closest to the center of the patterned block is located, and the point cloud of the entire back of the patterned block is fitted using the known radius. All 3D points are back-projected onto the image coordinate system. Using the precise localization result of the left camera image as a reference, the corresponding hole in the right camera image is found. An NCC template is created based on the hole in the left image, and the hole is found at the corresponding position in the right image. The coordinates of the right image are corrected, and finally, the 3D coordinates of all holes in the stereo system are obtained. , where the superscript n is the hole number.

5. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 4, characterized in that, Step S6 specifically involves: first, fitting a straight cylinder based on the point cloud formed by all the holes to obtain the coordinate system of the patterned block. Its origin is at the highest point of the fitted cylinder's side surface, the X-axis is parallel to the cylinder's axis, and the Z-axis points to the cylinder's geometric center. Then, the entire patterned block area is located and divided into 60 rectangular regions. The 3D coordinates of the holes in each region are projected onto the cylinder's bottom surface for circle fitting. The highest point of this circle in the patterned block coordinate system is obtained and projected back into 3D space. Finally, based on the 60 highest points, the highest generatrix in the initial patterned block coordinate system is fitted. The direction of this generatrix is ​​then used to adjust the patterned block coordinate system. Perform corrections.

6. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 5, characterized in that, Step S7 specifically involves: combining target detection with traditional image processing methods to obtain the center line of the groove; based on the pattern block coordinate system obtained in step S6 and the known radius information, establishing a point cloud set on the back of the pattern block; calculating the projection coordinate set of the point cloud in the left image; finding the line connecting the projection point closest to the center line of the groove; and the point cloud coordinates corresponding to the projection point are the point cloud coordinates corresponding to the center line of the groove.

7. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 6, characterized in that, Step S8 specifically involves correcting the Z-axis coordinates of the 3D coordinates of all back holes obtained in step S5 based on the point cloud model established in step S7: First, find the coordinates closest to the back hole in the 2D projection coordinate set of the point cloud in the left image, and use the Z-axis coordinates of the point cloud corresponding to these coordinates to replace the back hole coordinates. The Z-axis coordinates are calculated; the point on the trench centerline point cloud closest to the 3D coordinates of the back hole is calculated to obtain the position of the trench corresponding to all holes. .

8. The control method for an automatic milling device for tire tread blocks based on binocular 3D vision according to claim 6, characterized in that, Step S9 specifically involves: First, according to... Backhole coordinates in camera coordinate system Transform to the machine tool coordinate system, that is: ,in This only includes the 3D coordinate information of the holes. Additionally, it's necessary to calculate the angle of rotation of the machine tool's A-axis when all holes reach their highest point after rotating around the machine tool's X-axis. This angle is the rotation axis coordinate system. In the YZ plane, calculate the angle between the line connecting the center of rotation and the hole and the Z-axis, then calculate the rotation of the hole around the axis of rotation. The coordinates after the angle give the pose of the rotated hole. Similarly, the pose of the groove corresponding to the rotated hole can be obtained. ; Based on the photo-taking pose recorded in step S3 The position of the milling cutter aligned with the hole closest to the center of the pattern block. The position of the patterned block closest to the center hole ; The position the machine tool needs to reach when calculating the chamfer. ,in: , , Similarly, the position that the machine tool needs to reach when milling grooves can be obtained.

Images