Machining correction method and equipment and storage medium

Abstract

The invention discloses a processing correction method and device and a storage medium, and relates to the technical field of image processing. According to the method, the feature points in the to-be-processed material image are identified, and the feature matching image and the feature matching algorithm are determined according to the shape features of the feature points; determining the similarity between the feature points in the to-be-processed material image and the feature points in the feature matching image according to a feature matching algorithm, and determining target feature points in the to-be-processed material image according to the similarity; when the number of the target feature points is greater than or equal to a preset number threshold, determining a compensation parameter according to the pixel coordinates of the target feature points and the calibration coordinates of the feature points in the feature matching image; and the cutting path is calibrated according to the compensation parameters. According to the method, the shape features and complexity of the feature points are considered, and the feature matching algorithm and the number threshold are dynamically determined, so that the correction precision is adjusted according to the material features and the processing requirements under the condition that the material may deform, and the flexibility of processing correction is enhanced.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a processing correction method, device and storage medium. Background Art

[0002] In laser cutting technology, certain special materials, such as colloids, are susceptible to high temperatures and other mechanical effects during the laser cutting process, causing material deformation and thus affecting processing accuracy. To compensate for this material deformation, traditional laser cutting systems typically apply a pre-defined correction algorithm during the process.

[0003] However, due to differences in the physical properties of materials, the degree of deformation during processing varies. Furthermore, different processing tasks also require different calibration accuracy. Traditional pre-processing camera calibration cannot reflect the material's deformation during processing in real time. Traditional calibration methods cannot adapt to different material properties and processing requirements, resulting in low calibration flexibility.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a processing correction method, equipment and storage medium, aiming to solve the technical problem that traditional correction methods cannot be adaptively adjusted according to the characteristics of different materials and processing requirements.

[0006] To achieve the above objectives, the present application proposes a processing correction method, which includes: Identify feature points in the image of the material to be processed, and determine a feature matching image and a feature matching algorithm based on the shape characteristics of the feature points; Determining, according to the feature matching algorithm, similarities between feature points in the image of the material to be processed and feature points in the feature matching image, and determining target feature points in the image of the material to be processed according to the similarities; When the number of the target feature points is greater than or equal to a preset number threshold, determining compensation parameters according to the pixel coordinates of the target feature points and the calibrated coordinates of the feature points in the feature matching image; The cutting path is calibrated according to the compensation parameters.

[0007] In one embodiment, the shape features include corner features and contour features, and the step of determining a feature matching image and a feature matching algorithm based on the shape features of the feature points includes: determining the feature matching image according to the contour features of the feature points; determining the complexity of the feature point according to the corner feature and the contour feature of the feature point; A corresponding feature matching algorithm is determined according to the complexity.

[0008] In one embodiment, before the step of identifying feature points in the image of the material to be processed and determining a feature matching image and a feature matching algorithm based on the shape features of the feature points, the step further includes: Determining the preset number threshold according to the complexity of the feature points, wherein the complexity is inversely proportional to the preset number threshold; or Acquire a quantity parameter input by a user, and use the quantity parameter as the preset quantity threshold.

[0009] In one embodiment, the step of determining the compensation parameter according to the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image includes: Based on the camera parameters and the image of the material to be processed, the pixel coordinates of the target feature points are converted into calibration coordinates; The coordinate offset of the feature point in the image of the material to be processed is determined according to the calibrated coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image, and the coordinate offset is used as the compensation parameter.

[0010] In one embodiment, the step of determining the compensation parameter based on the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image further includes: Moving the camera's field of view to the target feature point, and controlling the camera to capture an image of the target feature point; Based on the camera parameters and the target feature point image, the pixel coordinates of the target feature point are converted into calibration coordinates; The coordinate offset of the feature point in the image of the material to be processed is determined according to the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image, and the coordinate offset is used as the compensation parameter.

[0011] In one embodiment, the step of calibrating the cutting path according to the compensation parameters includes: determining an offset of each cutting path point on the cutting path according to the compensation parameter; offsetting each of the cutting path points according to the offset amount of the cutting path point; A new cutting path is generated between the offset cutting path points through the interpolation algorithm.

[0012] In one embodiment, the step of calibrating the cutting path according to the compensation parameters further comprises: determining an offset of each cutting path point on the cutting path according to the compensation parameter; determining a scaling ratio of the cutting path according to the offset of the cutting path point; The cutting path is corrected according to the scaling ratio.

[0013] In one embodiment, after the step of calibrating the cutting path according to the compensation parameters, the method further includes: According to the offset of the first point on the cutting path, the feeding offset length for the next feeding is determined, and the feeding offset length is sent to the feeding device.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a processing correction device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the processing correction method described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the processing correction method described above are implemented.

[0016] The present application provides a processing correction method, which identifies feature points in an image of a material to be processed, determines a feature matching image and a feature matching algorithm based on the shape features of the feature points; then, based on the feature matching algorithm, determines the similarity between the feature points in the image of the material to be processed and the feature points in the feature matching image, and determines the target feature points in the image of the material to be processed based on the similarity; when the number of target feature points is greater than or equal to a preset number threshold, determines compensation parameters based on the pixel coordinates of the target feature points and the calibrated coordinates of the feature points in the feature matching image; and calibrates the cutting path based on the compensation parameters.

[0017] This method accurately identifies and matches feature points in the image of the material to be processed, takes into account the shape characteristics and complexity of the feature points, dynamically determines the feature matching algorithm and quantity threshold, and calculates compensation parameters to calibrate the cutting path. In the case of possible material deformation, this method improves processing positioning accuracy and product consistency, reduces processing errors, and enhances the flexibility of automated processing correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A schematic diagram of the process flow provided for Example 1 of the machining correction method of this application; Figure 2 A schematic diagram of the process flow provided for Example 2 of the machining correction method of this application; Figure 3 A schematic diagram of the process flow provided for Example 3 of the machining correction method of this application; Figure 4 Schematic diagram of the equipment structure of the hardware operating environment involved in the processing correction method in the embodiment of the present application.

[0021] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not intended to limit the present application.

[0023] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0024] In laser cutting technology, certain special materials, such as colloids, are easily affected by high temperatures and other mechanical movements during the laser cutting process, causing the material to deform, which in turn affects the processing accuracy. In order to compensate for material deformation, traditional laser cutting systems usually apply a predetermined correction algorithm for correction during the processing. However, due to differences in the physical properties of the materials themselves, the degree of deformation during the processing varies. In addition, different processing tasks have different requirements for correction accuracy. Traditional pre-processing camera calibration cannot reflect the deformation of the material during the processing in real time. Traditional correction methods cannot be adaptively adjusted according to the characteristics of different materials and processing requirements, and the correction flexibility is low.

[0025] In view of the above problems, the present application proposes a processing correction method, which identifies feature points in the image of the material to be processed, determines a feature matching image and a feature matching algorithm based on the shape characteristics of the feature points; then, based on the feature matching algorithm, determines the similarity between the feature points in the image of the material to be processed and the feature points in the feature matching image, and determines the target feature points in the image of the material to be processed based on the similarity; when the number of target feature points is greater than or equal to a preset number threshold, determines the compensation parameters based on the pixel coordinates of the target feature points and the calibrated coordinates of the feature points in the feature matching image; and calibrates the cutting path based on the compensation parameters.

[0026] This method accurately identifies and matches feature points in the image of the material to be processed, takes into account the shape characteristics and complexity of the feature points, dynamically determines the feature matching algorithm and quantity threshold, and calculates compensation parameters to calibrate the cutting path. In the case of possible material deformation, this method improves processing positioning accuracy and product consistency, reduces processing errors, and enhances the flexibility of automated processing correction.

[0027] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, or an electronic device capable of implementing the above functions. The following uses a processing correction system as an example to illustrate this embodiment and the following embodiments.

[0028] Based on this, the first embodiment proposed in this application provides a processing correction method, referring to Figure 1 In this embodiment, the processing correction method includes steps S10 to S40: Step S10 , identifying feature points in the image of the material to be processed, and determining a feature matching image and a feature matching algorithm according to shape features of the feature points.

[0029] It should be noted that during the laser processing process, due to the physical properties of the material to be processed, it may be deformed during the processing due to high temperature and other reasons, such as stretching or curling. In this embodiment, in order to ensure that the material to be processed is easy to position during the processing, feature points are provided on the material to be processed to assist in positioning. The feature points can be arranged in the form of an array on the material to be processed, or they can be located at the center of the material to be processed. In addition, the shape of the feature points can be adjusted according to the type of material to be processed or the processing accuracy. For example, for materials to be processed that are not easily deformed or for materials to be processed that do not require high processing accuracy, the feature points can be set to circles. For materials to be processed that are relatively easy to deform or for materials to be processed that require high processing accuracy, the feature points can be set to more complex graphics such as stars.

[0030] Understandably, for materials that are less prone to deformation, they are relatively stable during processing, with small and regular deformations. Circular feature points are simple and symmetrical, meeting positioning requirements while reducing the computational complexity of subsequent feature point matching. On the other hand, for materials that are more easily deformed, their deformations are larger and more irregular. Feature points in complex shapes like star shapes contain more detail and directional information, allowing them to maintain good recognizability and matching after deformation, thereby more accurately reflecting the material's actual deformation.

[0031] For example, a camera is first used to capture an image of the material to be processed, ensuring that the image is clear and accurately reflects the material's characteristics. The captured image is then preprocessed, such as grayscale conversion and denoising, to improve the accuracy of feature point detection. For example, a Gaussian filter can be used to remove noise from the image, making it smoother and facilitating subsequent feature point detection.

[0032] After collecting the image of the material to be processed, feature points in the image are identified through feature point detection algorithms such as the SIFT (Scale-Invariant Feature Transform) algorithm.

[0033] For example, a scale-space pyramid is constructed by repeatedly Gaussian blurring and downsampling an image. Specifically, the image of the material being processed is first Gaussian blurred a preset number of times. Each blurring step reduces image detail, thereby simulating image features at different scales. The blurred images are then downsampled sequentially from fine to coarse scales, reducing the image resolution. This constructs a Gaussian pyramid. For example, assuming the original image size is W × H, the first downsampling step reduces the image size to W / 2 × H / 2, the second downsampling step reduces it to W / 4 × H / 4, and so on, forming a multi-layered pyramid structure in the scale space. W represents the horizontal dimension of the image, i.e., the number of pixels in the horizontal direction; H represents the vertical dimension, i.e., the number of pixels in the vertical direction. The purpose of constructing a scale space is to detect image features at different scales, making feature point detection robust to image scaling. Gaussian blurring and downsampling capture image details and overall structural information at different resolutions, enabling subsequent feature point detection to identify significant feature points at different scales.

[0034] In the constructed scale space, each pixel is compared with its neighboring pixels. Specifically, for each pixel in the current layer, its values ​​are compared with a first preset number of adjacent pixels in the same layer, such as 8 pixels, and a second preset number of corresponding pixels in the upper and lower layers, such as 9 pixels. If the value of a pixel is a maximum or minimum within its neighborhood, it is considered a potential extreme point, that is, a possible feature point.

[0035] The detected extreme points are then further analyzed and screened. First, the curvature of each extreme point is calculated, and the stability of the extreme point is determined based on the magnitude of the curvature. If the curvature is too large, it indicates that the extreme point is located on an edge, susceptible to noise, and unstable, and needs to be removed. The remaining extreme points are considered identified as feature points. Then, for each of these extreme points, their pixel coordinates are determined by fitting a quadratic function to determine the location of the feature point.

[0036] After identifying the feature points in the image of the material to be processed, the appropriate feature matching image and feature matching algorithm are determined based on the shape characteristics of the feature points. The feature matching image can be a standard template image built into the processing correction system, or an image of the same type as the material to be processed but without deformation. It contains the feature points on the material and their location information, which is used to match the feature points in the image of the material to be processed.

[0037] It is understandable that feature points of different shapes present different visual characteristics in the image. For example, a circular feature point appears as a relatively regular circular outline in the image, and its matching image should also have similar circular features so that the corresponding point can be accurately found during the matching process. Feature points of complex shapes such as stars have more corners and detailed information, and the matching image needs to be able to reflect these complex shape features in order to better match. Feature points of different shapes have different requirements for the performance of the matching algorithm. Feature points of simple shapes such as circles are more suitable for using some fast and simple matching algorithms because their features are relatively simple and it is easy to find the corresponding points through basic geometric shape matching. Feature points of complex shapes such as stars require more complex matching algorithms that need to be able to handle complex shape information and possible deformations to ensure the accuracy and reliability of the matching.

[0038] Optionally, step S10 includes steps S11 to S13: Step S11: determining the feature matching image according to the contour features of the feature points.

[0039] After identifying the feature points in the image of the material to be processed, the contour information of the feature points is extracted through the edge detection algorithm, the boundary pixels of the feature points are identified, and then the boundary pixels of the feature points are connected into one or more continuous curves or broken lines through the contour detection algorithm to form the contour features of the feature points.

[0040] Exemplarily, the Canny edge detection algorithm is used to extract the contour information of the feature points. Specifically, the gradient of the image in the horizontal and vertical directions is calculated by the Sobel operator or the Prewitt operator to obtain the gradient amplitude and direction, and the gradient amplitude is suppressed to a non-maximum value, the maximum value points in the edge direction are retained, and other points are suppressed to refine the edge. Then a high threshold and a low threshold are set, and the points with a gradient amplitude higher than the high threshold are regarded as strong edge points, the points with a gradient amplitude lower than the low threshold are regarded as non-edge points, and the points with a gradient amplitude between the two are regarded as weak edge points. Weak edge points with strong edge points in the neighborhood are connected to finally obtain a clear edge map. Next, the edge map is binarized and a threshold is set to convert the edge map into a binary image. Then, by scanning the binary image, all connected edge pixel points are found to form contour features.

[0041] Optionally, standard shape templates corresponding to different feature points may be predefined in the processing correction system, and the extracted contour features may be matched with the predefined standard shape templates to determine the graphic category of the feature points, and further determine the feature matching image.

[0042] Step S12: determining the complexity of the feature point according to the corner feature and the contour feature of the feature point.

[0043] Exemplarily, a corner detection algorithm is used to identify corners on feature points. Corner points are points in an image with obvious changes in direction, and usually appear at the edges and corners of objects. For feature points of complex shapes, such as stars, there will be multiple corner points inside, while feature points of simple shapes, such as circles, have almost no obvious corner points. The extracted corner point features, such as the number and distribution of corner points, and contour features are combined to evaluate the complexity of the feature points. For example, if a feature point contains a large number of corner points and the contour shape is complex, such as a polygon or a star, the complexity of the feature point is considered to be high; conversely, if the feature point has almost no corner points and the contour is simple, such as a circle or a square, the complexity is low.

[0044] Specifically, a complexity index is defined, which combines the number of corner points, the change in contour curvature and other parameters by weighting to obtain a specific complexity value. For example, the complexity index C can be expressed as: .in, is the number of corner points, is the variance of the profile curvature, and is the weight coefficient.

[0045] Step S13: determining a corresponding feature matching algorithm according to the complexity.

[0046] Exemplarily, a comparison table is maintained within the processing correction system to record the feature matching algorithms corresponding to different complexity indicators. For example, for low-complexity feature points without corners, matching is performed based on the edge map of the feature points using a square difference matching algorithm or a normalized cross-correlation matching algorithm. For feature points with a small number of corners, matching is performed using a matching method based on geometric transformation, such as calculating the affine transformation or homography matrix between the feature points in the image of the material to be processed and the feature points in the feature matching image. For complex feature points with a large number of corners and high changes in contour curvature, feature-based matching algorithms such as SIFT, SURF (Speeded Up Robust Features), and ORB (Oriented FAST and Rotated BRIEF) are used to extract local feature descriptors of the feature points, and matching is performed by comparing the similarity between the descriptors.

[0047] Step S20 , determining similarities between feature points in the image of the material to be processed and feature points in the feature matching image according to the feature matching algorithm, and determining target feature points in the image of the material to be processed according to the similarities.

[0048] It is understood that since the feature points in the feature matching image are all identical, the similarity between all feature points identified in the image of the material to be processed and any feature point in the feature matching image can be calculated. When the similarity between a feature point in the image of the material to be processed and any feature point in the feature matching image exceeds a preset similarity threshold, the feature point in the image of the material to be processed is determined to be a target feature point.

[0049] Optionally, a descriptor is calculated for each feature point in the image of the material to be processed, and its distance to the descriptor of any feature point in the feature matching image is calculated, such as Euclidean distance or Hamming distance. The smaller the distance between the descriptors of the two feature points, the higher the similarity.

[0050] It should be noted that a feature descriptor is a vector used to describe the characteristics of the area around a feature point. It can uniquely represent the image information of that area, has high uniqueness, and is invariant to changes in lighting and viewing angle. The calculation method of the feature descriptor varies depending on the feature matching algorithm used. It can be a SIFT feature descriptor, a BRIEF feature descriptor, or other descriptors.

[0051] Step S30 : When the number of the target feature points is greater than or equal to a preset number threshold, compensation parameters are determined according to the pixel coordinates of the target feature points and the calibrated coordinates of the feature points in the feature matching image.

[0052] Optionally, step S30 includes steps S31-S32: Step S31 : based on the camera parameters and the image of the material to be processed, the pixel coordinates of the target feature points are converted into calibration coordinates.

[0053] Step S32 , determining the coordinate offset of the feature point in the image of the material to be processed according to the calibrated coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image, and using the coordinate offset as the compensation parameter.

[0054] For example, the machining correction system first counts the number of target feature points identified in the image of the material to be machined using a feature matching algorithm. If the number of target feature points falls below a preset threshold, the machining correction system will indicate that there are insufficient feature points and prompt the user to re-identify the feature points or adjust the parameters of the feature matching algorithm.

[0055] If the number of target feature points is greater than or equal to a preset number threshold, the pixel coordinates of each target feature point in the image of the material to be processed are extracted. The pixel coordinates usually take the upper left corner of the image as the origin and represent the position of the feature point in pixels. At the same time, the calibration coordinates of the feature points corresponding to each target feature point on the feature matching image are obtained, and the pixel coordinates of the target feature points are converted into calibration coordinates using the camera intrinsic parameter matrix and distortion coefficient obtained during the camera calibration process. Then, based on the calibration coordinates of each target feature point and the calibration coordinates of the feature points corresponding to each target feature point on the feature matching image, the offset is calculated as a compensation parameter. Among them, the calibration coordinates refer to the conversion of pixel coordinates into coordinates in the normalized camera coordinate system through the camera intrinsic parameter matrix and distortion coefficient during the camera calibration process.

[0056] Optionally, step S30 further includes steps S33 to S35: Step S33: Move the camera's field of view to the target feature point, and control the camera to capture an image of the target feature point.

[0057] Step S34 : based on the camera parameters and the target feature point image, convert the pixel coordinates of the target feature point into calibration coordinates.

[0058] Step S35 , determining the coordinate offset of the feature point in the image of the material to be processed according to the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image, and using the coordinate offset as the compensation parameter.

[0059] To improve the accuracy of compensation parameter calculation, after the target feature point is located in the image of the material to be processed, the camera is controlled to move to the target feature point and capture an image of the target feature point again. The pixel coordinates of the target feature point are determined based on the image of the target feature point, rather than the entire image of the material to be processed.

[0060] For example, when camera calibration uses a less accurate calibration algorithm, such as the proportional calibration method, the accuracy of the camera's intrinsic parameter matrix and distortion coefficients may be affected, resulting in a decrease in the accuracy of the pixel coordinates of the target feature point determined from the entire image. In this case, by controlling the camera's field of view to move to the target feature point and capturing an image, a high-resolution local image of the feature point can be obtained. Compared to the entire image, the local image reduces the effects of background interference and image distortion, making the feature point clearer, thereby effectively compensating for errors caused by insufficient calibration accuracy and improving the calculation accuracy of the compensation parameters.

[0061] The pixel coordinates of the target feature points are determined according to the target feature point image. At the same time, the camera intrinsic parameter matrix and distortion coefficient obtained during the camera calibration process are used to convert the pixel coordinates of the target feature points into calibration coordinates. Then, the offset between the calibration coordinates of the target feature points and the corresponding feature points on the feature matching image is calculated as the compensation parameter.

[0062] Step S40: calibrating the cutting path according to the compensation parameters.

[0063] Once the compensation parameters are obtained, the predetermined cutting path can be calibrated based on the determined compensation parameters. The calibration process involves shifting, rotating, or scaling each cutting point along the cutting path according to the compensation parameters. The calibrated cutting path is then sent to the laser cutting control system, guiding the laser cutting head for precise machining. The calibrated cutting path more closely resembles the ideal path after material deformation during actual machining.

[0064] Optionally, step S40 includes steps S41 to S43: Step S41: determining the offset of each cutting path point on the cutting path according to the compensation parameter.

[0065] The cutting path is imported into the machining correction system before machining. The cutting path consists of a series of ordered cutting path points, each with its own predetermined coordinate position. For each cutting path point on the cutting path, the corresponding compensation parameters are assigned based on its positional relationship with nearby feature points.

[0066] Exemplarily, each cutting path point is spatially matched with an identified feature point. The distance between each cutting path point and at least two of the nearest feature points is calculated. Based on the ratio of the distances between the cutting path point and the feature points, a coordinate offset of the feature point is assigned to the cutting path point according to the distance ratio, and the offset of the cutting path point is calculated using linear interpolation.

[0067] For example, suppose there is a cutting path point P, and two feature points A and B nearby. The compensation parameter of A is ΔA, and the compensation parameter of B is ΔB. The distance between P and A is dPA, and the distance between P and B is dPB. Using linear interpolation, first calculate the weight of the target feature point, where the weight of feature point A is , the weight of feature point B Then calculate the offset assigned to the cutting path point P .

[0068] Step S42: offset each cutting path point according to the offset amount of the cutting path point.

[0069] Step S43: generating a new cutting path between the offset cutting path points by using a difference algorithm.

[0070] Add the original coordinates of the cutting path points to the offset to obtain the adjusted new cutting path points, and offset the cutting path points. Between each pair of adjacent offset cutting path points, a series of interpolation points are generated according to the selected interpolation algorithm. Based on the newly generated interpolation points and the offset cutting path points, a new cutting path is generated.

[0071] Optionally, step S40 further includes steps S44 to S46: Step S41: determining the offset of each cutting path point on the cutting path according to the compensation parameter.

[0072] Step S42: determining the scaling ratio of the cutting path according to the offset of the cutting path point.

[0073] Step S43: Correcting the cutting path according to the scaling ratio.

[0074] Optionally, an influence radius is set and the distance between each cutting path point and the feature points within the influence radius is calculated. Based on the distance ratio between the cutting path point and the feature points within the influence radius, the coordinate offset of the feature point is assigned to the cutting path point according to the distance ratio, and the offset of the cutting path point is calculated using linear interpolation.

[0075] For example, create an array A to store the offset of each cutting path point. Initialize two variables, total_dx and total_dy, to 0 to accumulate the X and Y offsets of all points. Initialize the variable count to the number of cutting path points. For each point i on the cutting path (from 1 to count), read the X offset dx_i and Y offset dy_i of point i based on the compensation parameters. Calculate the average X offset (average_dx = total_dx / count) and the average Y offset (average_dy = total_dy / count). Then, determine the maximum X coordinate value (max_x) and maximum Y coordinate value (max_y) of the original cutting path, and calculate the X scale (scale_x = (average_dx / max_x) + 1) and the Y scale (scale_y = (average_dy max_y) + 1). After determining the scale, check whether it is within a reasonable range. For example, the scale should not be less than 0.5 or greater than 2. Next, create a new array scaled_path to store the scaled cutting path points. For each point i on the original cutting path, first read the original coordinates x_i and y_i, and calculate the scaled coordinates and And add the scaled coordinates to the scaled_path array: scaled_path[i]=[scaled_x_i,scaled_y_i]. Finally, the scaled_path array is output as the corrected cutting path, and the path planner of the cutting system is updated to use the new cutting path for processing.

[0076] In this embodiment, by accurately identifying and matching feature points in the image of the material to be processed, and taking into account the shape characteristics and complexity of the feature points, the feature matching algorithm and quantity threshold are dynamically determined, and the compensation parameters are calculated to calibrate the cutting path. In this way, when the material may be deformed, the processing positioning accuracy and product consistency are significantly improved, the processing errors are reduced, the efficiency and stability of automated processing are enhanced, and efficient and precise processing control is achieved.

[0077] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 After step S40, the processing correction method further includes step S50: Step S50: determining a feeding offset length for the next feeding according to the offset of the first point on the cutting path, and sending the feeding offset length to the feeding device.

[0078] It is understood that adjusting the loading length during the cutting process can compensate for inaccurate material positioning caused by material deformation. By adjusting the offset during loading, the starting position of the cut can be aligned with the expected position of the material, thereby improving cutting accuracy and processing quality.

[0079] For example, the offset of the first point of the cutting path is read from the offset array offsets calculated previously, that is, offsets[0], which contains dx1 and dy1. Based on the offsets dx1 and dy1 of the first point, the offset length during loading is calculated. For example, if the loading device is in the X direction, the loading offset length in the X direction is calculated: , where conversionFactorX is the conversion factor that converts the offset from cutting path units to loading device length units. Similarly, if the loading device is in the Y direction, calculate the Y direction loading offset length: , where conversionFactorY is the conversion factor in the Y direction. The calculated loading offset length is then sent to the loading device, which controls the loading device to update its internal parameters so that it can compensate for material deformation during the next loading.

[0080] In this embodiment, by compensating for the offset of the first point, the starting point of the cutting path is ensured to be accurately aligned with the actual position of the material, thereby improving the overall cutting accuracy. Accurate loading offset can reduce material waste due to inaccurate positioning and improve material utilization.

[0081] Based on the above embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 3 Before step S10, the processing correction method further includes steps S60 to S70: Step S60: determining the preset number threshold according to the complexity of the feature points, wherein the complexity is inversely proportional to the preset number threshold.

[0082] It is understood that by adjusting the preset number threshold of target feature points, the accuracy of positioning correction can be adjusted. Because the accuracy of positioning correction depends on the number and quality of the feature points used for correction, more feature points can provide more data points to establish a positioning baseline, thereby improving the accuracy of correction. When more feature points are used, the errors in the identification or matching of individual feature points can be statistically averaged, reducing the impact on the final correction result. Different processing tasks may have different accuracy requirements. By adjusting the preset number threshold, these different requirements can be accommodated. For example, for tasks requiring high precision, the preset number threshold can be increased to use more feature points for matching and positioning. Similarly, different materials or image conditions may lead to differences in the quality of feature points. In this case, the correction strategy can be adjusted according to the complexity of the feature points by adjusting the threshold. For example, if the complexity of the feature points is high, that is, the matching accuracy between each feature point is high, the number of feature points used for correction can be reduced to strike a balance between correction accuracy and processing efficiency.

[0083] For example, each identified feature point is analyzed based on its corner and contour features to quantify its complexity. Complexity can be a numerical value representing the geometric or textural complexity of the feature point. A function or mapping rule is defined to convert the complexity of the feature point into a preset threshold number. This relationship is inversely proportional: the higher the complexity, the lower the threshold number of required feature points.

[0084] Step S70: Acquire a quantity parameter input by the user, and use the quantity parameter as the preset quantity threshold.

[0085] In order to allow users to customize the calibration accuracy according to specific application scenarios and needs, the processing correction system can support manual input of a quantity parameter as a preset quantity threshold, thereby providing a method for users to customize the calibration accuracy.

[0086] For example, an input box or knob is provided on the cutting device's user interface, allowing the user to enter or adjust a quantity parameter. In response to the user's input, the quantity parameter value entered by the user is obtained and set as a preset quantity threshold for subsequent feature point quantity determination. Users can customize calibration accuracy based on material characteristics and processing requirements, enhancing their control over the processing process.

[0087] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the processing and correction method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0088] The present application provides a processing correction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the processing correction method in the above-mentioned embodiment one.

[0089] Reference below Figure 4 , which shows a schematic diagram of the structure of a processing and correction device suitable for implementing the embodiment of the present application. The processing and correction device in the embodiment of the present application may include but is not limited to a fixed terminal such as a laser cutter. Figure 4 The processing correction device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0090] like Figure 4 As shown, the machining and correction device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the machining and correction device. The processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication devices 1009. Communication device 1009 can allow the machining correction device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a machining correction device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or provided instead.

[0091] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0092] The machining correction device provided in this application, utilizing the machining correction method described in the aforementioned embodiment, can address the technical issue of conventional correction methods being unable to adaptively adjust to different material properties and machining requirements. Compared to the prior art, the machining correction device provided in this application achieves the same beneficial effects as the machining correction method described in the aforementioned embodiment. Other technical features of this machining correction device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0093] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0094] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0095] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the machining correction method in the above-mentioned embodiment.

[0096] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0097] The computer-readable storage medium may be included in the processing and correction device; or it may exist independently without being assembled into the processing and correction device.

[0098] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the machining and correction device, the machining and correction device can write computer program code for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, or as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, via the Internet using an Internet service provider).

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0100] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0101] The computer-readable storage medium provided herein stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned machining correction method. This computer-readable storage medium addresses the technical issue of conventional correction methods being unable to adaptively adjust to different material properties and machining requirements. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided herein are similar to those of the machining correction method provided in the aforementioned embodiments and are not further elaborated here.

[0102] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A processing correction method, characterized in that: The processing correction method comprises: Identify feature points in the image of the material to be processed, and determine a feature matching image and a feature matching algorithm based on the shape features of the feature points; Determine, according to the feature matching algorithm, the similarity between the feature points in the image of the material to be processed and the feature points in the feature matching image, and determine the target feature points in the image of the material to be processed according to the similarity; When the number of the target feature points is greater than or equal to a preset number threshold, determining compensation parameters according to the pixel coordinates of the target feature points and the calibrated coordinates of the feature points in the feature matching image; According to the compensation parameters, the cutting path is calibrated.

2. The processing correction method according to claim 1, characterized in that: The shape features include corner features and contour features, and the step of determining a feature matching image and a feature matching algorithm according to the shape features of the feature points includes: Determining the feature matching image according to the contour features of the feature points; Determining the complexity of the feature point according to the corner feature and the contour feature of the feature point; A corresponding feature matching algorithm is determined according to the complexity.

3. The processing correction method according to claim 2, characterized in that: Before the step of identifying feature points in the image of the material to be processed and determining a feature matching image and a feature matching algorithm according to the shape features of the feature points, the method further includes: Determining the preset number threshold according to the complexity of the feature points, wherein the complexity is inversely proportional to the preset number threshold; or Acquire a quantity parameter input by a user, and use the quantity parameter as the preset quantity threshold.

4. The processing correction method according to claim 1, characterized in that: The step of determining the compensation parameter according to the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image comprises: Based on the camera parameters and the image of the material to be processed, the pixel coordinates of the target feature points are converted into calibration coordinates; According to the calibrated coordinates of the target feature points and the calibrated coordinates of the feature points in the feature matching image, the coordinate offset of the feature points in the image of the material to be processed is determined, and the coordinate offset is used as the compensation parameter.

5. The processing correction method according to claim 1, characterized in that: The step of determining the compensation parameter according to the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image further includes: Move the camera's field of view to the target feature point, and control the camera to capture an image of the target feature point; Based on the camera parameters and the target feature point image, the pixel coordinates of the target feature point are converted into calibration coordinates; According to the pixel coordinates of the target feature point and the calibrated coordinates of the feature point in the feature matching image, the coordinate offset of the feature point in the image of the material to be processed is determined, and the coordinate offset is used as the compensation parameter.

6. The processing correction method according to claim 1, characterized in that: The step of calibrating the cutting path according to the compensation parameters comprises: Determining the offset of each cutting path point on the cutting path according to the compensation parameter; offsetting each of the cutting path points according to the offset amount of the cutting path point; A new cutting path is generated between the offset cutting path points through an interpolation algorithm.

7. The processing correction method according to claim 1, characterized in that: The step of calibrating the cutting path according to the compensation parameters further comprises: Determining the offset of each cutting path point on the cutting path according to the compensation parameter; Determining a scaling ratio of the cutting path according to the offset of the cutting path point; The cutting path is corrected according to the scaling factor.

8. The processing correction method according to any one of claims 6 to 7, characterized in that: After the step of calibrating the cutting path according to the compensation parameters, the method further includes: According to the offset of the first point on the cutting path, the offset length of the next material feeding is determined, and the offset length of the material feeding is sent to the material feeding device.

9. A processing and correction device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the machining correction method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the processing correction method according to any one of claims 1 to 8 are implemented.

Images