Bridge workpiece machining track generation method, device, equipment, medium and product

By acquiring the bridge workpiece images, extracting point cloud data and building a processing trajectory, the problems of edge unevenness and grinding inconsistencies caused by manual processing are solved, and the high accuracy and efficient processing of bridge workpieces are achieved.

CN119067938APending Publication Date: 2024-12-03SPEEDBOT ROBOTICS CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411143534.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, due to manual capacity limitations during the processing of bridge workpieces, the edges are uneven and the degree of polishing are inconsistent, which reduces the processing accuracy.

Method used

By obtaining the image of the bridge workpiece, extracting point cloud data, performing edge screening and building processing trajectory, achieving automated processing, reducing manual intervention, and ensuring consistent edge flatness and polishing.

Benefits of technology

Improve the machining accuracy and efficiency of bridge workpieces, ensuring that the edges are flat and the degree of polishing of parts of the same shape is consistent.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067938A_ABST
    Figure CN119067938A_ABST
Patent Text Reader

Abstract

The invention relates to a bridge workpiece machining track generation method and device, equipment, a medium and a computer program product. The bridge workpiece processing track generation method comprises the following steps: acquiring a workpiece image carrying features of a to-be-processed bridge workpiece, and extracting workpiece point cloud data from the workpiece image; performing workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data; and according to the edge point cloud data, constructing a processing track corresponding to the to-be-processed bridge workpiece. By adopting the method, the machining accuracy of the bridge workpiece can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of industrial production technology, and in particular to a method, device, equipment, medium and computer program product for generating a machining trajectory for a bridge workpiece. Background Art

[0002] With the development of industrial production technology, when building bridges, in order to prevent the bridge deck from deforming due to temperature changes, it is necessary to design bridge workpieces such as bridge expansion joints to avoid excessive deformation of the bridge deck that may cause damage to the bridge. Therefore, a method of accurately processing bridge workpieces is needed so that the bridge workpieces can avoid damage to the bridge.

[0003] At present, bridge workpieces are usually processed manually. However, due to the limitations of human capabilities, the edges of the processed bridge workpieces may be uneven. In addition, manual labor cannot ensure that the force used in each processing is consistent. Therefore, the degree of polishing of parts of the same shape of the processed bridge workpieces may be inconsistent, resulting in low processing accuracy of the bridge workpieces. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for generating a bridge workpiece machining trajectory that can improve the machining and detection accuracy of bridge workpieces in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for generating a machining trajectory of a bridge workpiece, comprising:

[0006] Acquire a workpiece image carrying features of a bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image;

[0007] Performing workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data;

[0008] A processing trajectory corresponding to the bridge workpiece to be processed is constructed based on the edge point cloud data.

[0009] In a second aspect, the present application also provides a bridge workpiece machining trajectory generating device, comprising:

[0010] An extraction module, used for acquiring a workpiece image carrying features of a bridge workpiece to be processed, and extracting workpiece point cloud data from the workpiece image;

[0011] A screening module, used for screening the workpiece edge of the workpiece point cloud data to obtain edge point cloud data;

[0012] A construction module is used to construct a processing trajectory corresponding to the bridge workpiece to be processed based on the edge point cloud data.

[0013] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0014] Acquire a workpiece image carrying features of a bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image;

[0015] Performing workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data;

[0016] A processing trajectory corresponding to the bridge workpiece to be processed is constructed based on the edge point cloud data.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0018] Acquire a workpiece image carrying features of a bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image;

[0019] Performing workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data;

[0020] A processing trajectory corresponding to the bridge workpiece to be processed is constructed based on the edge point cloud data.

[0021] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0022] Acquire a workpiece image carrying features of a bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image;

[0023] Performing workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data;

[0024] A processing trajectory corresponding to the bridge workpiece to be processed is constructed based on the edge point cloud data.

[0025] The above-mentioned bridge workpiece processing trajectory generation method, device, equipment, medium and computer program product obtain a workpiece image carrying the characteristics of the bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image; perform workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data; and construct a processing trajectory corresponding to the bridge workpiece to be processed based on the edge point cloud data, thereby realizing the automated generation process of the processing trajectory of the bridge workpiece to be processed. For each bridge workpiece to be processed, after the processing trajectory is generated, the bridge workpiece to be processed can be processed by automatic processing tools such as robotic arms, thereby reducing manual intervention in the processing process of the bridge workpiece to be processed to a certain extent, ensuring that the edges of the processed bridge workpieces are smooth, and the polishing degree of the processed bridge workpieces corresponding to the same shape is consistent, thereby improving the processing accuracy of the bridge workpieces. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A schematic diagram of an application scenario of a bridge workpiece machining trajectory generation method in one embodiment;

[0028] Figure 2 A schematic diagram of a flow chart of a method for generating a machining trajectory of a bridge workpiece in one embodiment;

[0029] Figure 3 It is a schematic structural diagram of a bridge workpiece to be processed in a scenario in an embodiment, where the bridge workpiece to be processed is a bridge span plate;

[0030] Figure 4 A schematic diagram of a process for extracting workpiece point cloud data from a workpiece image in a scenario in an embodiment;

[0031] Figure 5 It is a schematic diagram of a process of accurately screening edge point cloud data from workpiece point cloud data in a scenario in an embodiment;

[0032] Figure 6 It is a schematic diagram of the overall process of constructing a processing trajectory in a scenario in an embodiment;

[0033] Figure 7 It is a structural block diagram of a bridge workpiece machining trajectory generating device in one embodiment;

[0034] Figure 8FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] In the traditional method, the bridge workpiece is processed manually, but due to the limited ability of the human body, the edge of the processed bridge workpiece may be uneven. In addition, the manual force cannot guarantee the consistency of the force used in each processing. Therefore, the degree of grinding of the parts of the same shape of the processed bridge workpiece may be inconsistent, resulting in low processing accuracy of the bridge workpiece; or, the bridge workpiece is taught by a robot arm. Although this method can ensure that the edge of the processed bridge workpiece is flat and the degree of grinding of the parts of the same shape of the processed bridge workpiece is consistent, this method requires manual planning of the corresponding processing trajectory of the robot arm. At this time, the accuracy of bridge processing depends on the accuracy of the manually planned processing trajectory, that is, it depends on the professional ability of the manually planned processing trajectory. Therefore, the accuracy of bridge processing is still low. Therefore, there is an urgent need for a bridge workpiece processing trajectory generation method that improves the processing accuracy of bridge workpieces.

[0037] The bridge workpiece machining trajectory generation method provided in the embodiment of the present application can be applied to Figure 1 In the application scenario shown. Among them, the terminal 102 communicates with the camera 104 through the network, the camera 104 is used to collect the workpiece image carrying the features of the bridge workpiece to be processed, the terminal 102 communicates with the server 106 through the network, the terminal 102 communicates with the robot 108 through the network, the robot 108 is used to process the bridge workpiece to be processed, and the data storage system can store the workpiece image that the server 106 needs to process. The terminal 102 constructs a processing trajectory based on the workpiece image and sends the processing trajectory to the robot 108. When the robot 108 receives the processing trajectory, it processes the bridge workpiece to be processed according to the processing trajectory. The data storage system can be integrated on the server 106, or it can be placed on the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 106 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0038] In one embodiment, Figure 2As shown, a method for generating a machining trajectory of a bridge workpiece is provided, and the method is applied to Figure 1 The server 106 in the example is used as an example to illustrate, and the following steps are included:

[0039] Step 202 , obtaining a workpiece image carrying features of the bridge workpiece to be processed, and extracting workpiece point cloud data from the workpiece image.

[0040] The features of the bridge workpiece to be processed in step 202 are used to characterize the appearance features of the bridge workpiece to be processed. The bridge workpiece to be processed is a bridge workpiece waiting to be processed. The bridge workpiece type to be processed can be a bridge workpiece with a relatively complex processing shape such as Figure 3 The bridge seam plate shown may also be the scraps of bridge workpieces with relatively simple processing shapes, etc., which are not limited here. The workpiece image can be acquired by a camera, and the camera shooting angle can be other shooting angles that can fully display the features of the bridge workpiece to be processed in the workpiece image, such as the bridge workpiece to be processed; the camera shooting angle can also be multiple shooting angles that can display some features of the bridge workpiece to be processed in the image. At this time, the images acquired under multiple shooting angles are spliced ​​into the workpiece image. The workpiece point cloud data is used to characterize the processing shape of the bridge workpiece to be processed.

[0041] Exemplarily, obtaining a workpiece image carrying features of a bridge workpiece to be processed includes: obtaining a workpiece image carrying features of the bridge workpiece to be processed acquired by a camera.

[0042] As an embodiment, extracting workpiece point cloud data from a workpiece image includes: extracting workpiece power supply data for characterizing a corresponding machining shape of a bridge workpiece to be machined from the workpiece image.

[0043] Step 204 , screening the workpiece point cloud data for workpiece edges to obtain edge point cloud data.

[0044] Exemplarily, step 204 includes: performing workpiece edge screening on the workpiece point cloud data to obtain edge pixel points, and performing workpiece outer edge screening from the edge pixel points to obtain edge point cloud data.

[0045] Step 206: construct a processing trajectory corresponding to the bridge workpiece to be processed based on the edge point cloud data.

[0046] Exemplarily, step 206 includes: constructing an edge curve corresponding to the bridge workpiece to be processed according to the edge point cloud data, and determining the edge curve as a processing trajectory corresponding to the bridge workpiece to be processed.

[0047] In the above-mentioned bridge workpiece processing trajectory generation method, for the target workpiece to be processed, a workpiece image carrying the characteristics of the bridge workpiece to be processed is obtained, and workpiece point cloud data is extracted from the workpiece image; the workpiece point cloud data is screened for workpiece edges to obtain edge point cloud data; based on the edge point cloud data, a processing trajectory corresponding to the bridge workpiece to be processed is constructed, thereby realizing the automatic generation process of the processing trajectory of the bridge workpiece to be processed. For each bridge workpiece to be processed, after the processing trajectory is generated, the bridge workpiece to be processed can be processed by automatic processing tools such as robotic arms, thereby reducing manual intervention in the processing process of the bridge workpiece to be processed to a certain extent, and can ensure that the edges of the processed bridge workpieces are smooth, and the polishing degrees of the processed bridge workpieces corresponding to the same shape are consistent; and the processing trajectory is generated based on the workpiece image, and through workpiece edge screening and trajectory construction, the accuracy of the generated processing trajectory is guaranteed, thereby improving the processing accuracy of the bridge workpiece.

[0048] In order to ensure the machining accuracy of the bridge workpiece, a method for accurately extracting workpiece point cloud data from the workpiece image is required. In an exemplary embodiment, Figure 4 As shown, Figure 2 In step 202, extracting workpiece point cloud data from the workpiece image includes:

[0049] Step 302: Perform attribute filtering on the workpiece image to obtain a filtered image.

[0050] Exemplarily, step 302 includes: extracting a region for characterizing features of the to-be-processed bridge workpiece from the workpiece image to obtain a filtered image.

[0051] It is understandable that since the filtered image is subsequently used to generate a processing trajectory, and the processing trajectory is the basis for teaching the robotic arm to perform bridge processing, and if the processing trajectory is constructed based on the filtered image in the camera coordinate system, manual intervention is required when teaching the robotic arm to perform bridge processing based on the processing trajectory. This not only increases the process of manual intervention to convert the processing trajectory into the robotic arm coordinate system, but the accuracy of manual intervention to convert the processing trajectory into the robotic arm coordinate system also depends on the professionalism of the staff, resulting in lower processing accuracy and efficiency of bridge workpieces.

[0052] In order to solve the above-mentioned technical defect that if the processing trajectory is constructed by a filtered image in a camera coordinate system, manual intervention is required when teaching the robot arm to process the bridge based on the processing trajectory, resulting in low processing accuracy and processing efficiency of the bridge workpiece, as an embodiment, step 302: attribute filtering is performed on the area in the workpiece image used to characterize the characteristics of the bridge workpiece to be processed to obtain a regional image; according to the conversion relationship between the image coordinate system and the robot arm coordinate system, the regional image is converted into a filtered image.

[0053] In this way, the regional image in the camera's image coordinate system is converted into a filtered image in the robot arm coordinate system, which reduces the manual intervention in the process of converting the processing trajectory into the robot arm coordinate system, thereby improving the processing accuracy and efficiency of the bridge workpiece.

[0054] Furthermore, attribute filtering is performed on the area in the workpiece image used to characterize the features of the bridge workpiece to be processed to obtain a regional image, including: performing image recognition on the workpiece image to obtain a recognition result; and based on the recognition result, performing attribute filtering on the area in the workpiece image used to characterize the features of the bridge workpiece to be processed to obtain a regional image.

[0055] As one embodiment, according to the conversion relationship between the image coordinate system and the robotic arm coordinate system, the regional image is converted into a filtered image, including: the conversion relationship between the image coordinate system and the robotic arm coordinate system includes the conversion relationship between each coordinate axis between the image coordinate system and the robotic arm coordinate system, and the conversion relationship between each coordinate axis corresponding to the image coordinate system and the robotic arm coordinate system is obtained; according to the conversion relationship between each coordinate axis corresponding to the image coordinate system and the robotic arm coordinate system, the coordinates of each pixel point in the regional image are converted to obtain a filtered image.

[0056] Furthermore, the conversion relationship between each coordinate axis and the image coordinate system and the robotic arm coordinate system is obtained, including: for each coordinate axis, obtaining the first coordinate value of the preset point on the coordinate axis in the image coordinate system, and obtaining the second coordinate value of the preset point on the coordinate axis in the robotic arm coordinate system; according to the first coordinate value and the second coordinate value, determining the conversion relationship between the coordinate axis and the image coordinate system and the robotic arm coordinate system, specifically, determining the ratio between the first coordinate value and the second coordinate value as the conversion relationship between the coordinate axis and the image coordinate system and the robotic arm coordinate system.

[0057] Step 304: extracting point cloud data from the filtered image, and constructing a spatial plane equation based on the point cloud data.

[0058] Exemplarily, extracting point cloud data from a filtered image includes: determining pixel points in the filtered image as point cloud data.

[0059] Exemplarily, constructing a spatial plane equation based on point cloud data includes: selecting spatial point cloud data for fitting the spatial plane from the point cloud data, and constructing the spatial plane equation based on the spatial point cloud data.

[0060] As an embodiment, spatial point cloud data for fitting a spatial plane is selected from point cloud data, including: obtaining at least one preset fitting spatial plane, where the preset fitting space can be a spatial circle or a spatial plane of other shapes, which is not limited here; determining the distance between each point cloud data and the preset fitting spatial plane, and accumulating the number of points of the point cloud data in each preset fitting spatial plane whose corresponding distance is less than a preset distance threshold, determining the spatial plane with the largest number of corresponding points in each preset fitting spatial plane as the target fitting spatial plane, and determining the point cloud data in the target fitting spatial plane whose corresponding distance is less than a preset distance threshold as the spatial point cloud data for fitting the spatial plane, wherein the preset distance threshold is a preset critical value of the distance between the point cloud data and the preset fitting spatial plane when determining that the point cloud data belongs to a point within the preset fitting spatial plane.

[0061] The number of preset fitting space planes may be set by the user as required or according to fitting experience, for example, 2000.

[0062] Furthermore, the distance between each point cloud data and the preset fitting space plane is determined, including: for each point cloud data, obtaining the normal vector of the preset fitting space plane; determining the line vector composed of the point cloud data and any point on the preset fitting space plane; and determining the absolute value of the dot product between the line vector and the normal vector as the distance between the point cloud data and the preset fitting space plane.

[0063] Optionally, the absolute value of the dot product between the line vector and the normal vector is determined as the distance between the point cloud data and the preset fitting space plane, which can be expressed by the formula:

[0064]

[0065] in, is the distance between the point cloud data and the preset fitting space plane, Points on the preset fitting space plane With point cloud data The connecting vectors are composed of The normal vector of the preset fitting space plane.

[0066] Furthermore, obtaining at least one preset fitting space plane includes: arbitrarily selecting at least one fitting point cloud data group containing a preset number of point cloud data from the spatial point cloud data, and for each fitting point cloud data group in the at least one fitting point cloud data group, generating a preset fitting space plane according to the fitting point cloud data group, wherein the preset number can be 3 or other number of point cloud data that can generate a fitting space plane.

[0067] As one embodiment, a spatial plane equation is constructed based on spatial point cloud data, including: obtaining a preset plane equation, substituting the coordinate values ​​of the spatial point cloud data into the preset plane equation, and obtaining the spatial plane equation, wherein the preset plane equation is a preset plane equation containing unknown parameters, for example, Ax+By+Cz+D=0, and A, B, C, and D are unknown parameters.

[0068] Step 306 , based on the flatness information and the spatial plane equation corresponding to the bridge workpiece to be processed, the point cloud data is screened to obtain the workpiece point cloud data.

[0069] The flatness information in step 306 is used to characterize the degree of deviation of the actual surface of the bridge workpiece to be processed relative to the ideal surface.

[0070] It is understandable that the spatial plane equation constructed in the above manner is an ideal situation. However, when the bridge workpiece to be processed is large, it is possible that the preset distance threshold is set too small, resulting in a small number of point cloud data contained in the fitted spatial plane equation, which cannot accurately characterize the shape characteristics of the bridge workpiece to be processed.

[0071] In order to overcome the above-mentioned technical defect that the number of point cloud data contained in the fitted spatial plane equation is small due to the small preset distance threshold, and the shape characteristics of the bridge workpiece to be processed cannot be accurately characterized, as an embodiment, step 306 includes: generating a screening distance according to the flatness information corresponding to the bridge workpiece to be processed, wherein the flatness information is used to characterize the greater the deviation of the actual surface of the bridge workpiece to be processed relative to the ideal surface, the greater the screening distance; obtaining the distance between the point cloud data and the target fitting spatial plane corresponding to the spatial plane equation, and determining the point cloud data whose distance between the corresponding point cloud data and the target fitting spatial plane is less than the screening distance as the workpiece point cloud data.

[0072] In this way, after constructing the spatial plane equation, the point cloud data is further screened based on the spatial plane equation and flatness information, so that the screened workpiece point cloud data can accurately characterize the shape characteristics of the bridge workpiece to be processed.

[0073] In this embodiment, a filtered image is obtained by performing attribute filtering processing on the workpiece image; point cloud data is extracted from the filtered image, and a spatial plane equation is constructed based on the point cloud data; the point cloud data is screened according to the flatness information and the spatial plane equation corresponding to the bridge workpiece to be processed to obtain workpiece point cloud data, and a filtered image that can characterize the shape of the bridge workpiece to be processed is obtained through attribute filtering processing, and a spatial plane equation that can characterize the shape of the bridge workpiece to be processed is further constructed, and then based on the flatness information and the spatial plane equation, workpiece point cloud data that can accurately characterize the appearance characteristics of the bridge workpiece to be processed is finally obtained, thereby improving the accuracy of extracting the workpiece point cloud data.

[0074] In order to ensure the machining accuracy of the bridge workpiece, a method is needed to accurately filter the edge point cloud data from the workpiece point cloud data. In an exemplary embodiment, Figure 5 As shown, Figure 2 In step 204, the workpiece point cloud data is subjected to workpiece edge screening to obtain edge point cloud data, including:

[0075] Step 402 : Map the workpiece point cloud data into a workpiece grayscale image, traverse each pixel point in the workpiece grayscale image, and select edge pixel points from each pixel point in the workpiece grayscale image.

[0076] Exemplarily, mapping the workpiece point cloud data into a workpiece grayscale image includes: the workpiece grayscale image is composed of a first pixel point and a second pixel point, generating a first pixel point in the workpiece grayscale image whose pixel grayscale value is a preset first grayscale value according to the workpiece point cloud data, and setting the pixel points in the workpiece grayscale image other than the first pixel point to a second pixel point whose pixel grayscale value is a preset second grayscale value, wherein the preset first grayscale value can be 225, and the preset second grayscale value can be 0.

[0077] Exemplarily, traversing each pixel point in the workpiece grayscale image, selecting edge pixel points from each pixel point in the workpiece grayscale image, including: for each pixel point in the workpiece grayscale image, constructing eight-neighborhood information of the pixel point, wherein the eight-neighborhood information is used to characterize pixel value information of eight pixel points adjacent to the pixel point; accumulating the number of workpiece pixel points that belong to the pixel point in the eight-neighborhood information of the pixel point and characterizing the characteristics of the bridge workpiece to be processed, if the number of workpiece pixel points corresponding to the eight-neighborhood information of the pixel point belongs to a preset number range, then the pixel point is determined as an edge pixel point, wherein the preset number range can be (2,6) or other ranges set on demand or based on experience, which are not limited here.

[0078] Step 404: cluster the edge pixels to obtain cluster information.

[0079] Exemplarily, step 404 includes: clustering the edge pixels according to the relationship between the edge pixels by a preset clustering method to obtain cluster cluster information, wherein the preset clustering method includes but is not limited to a K-means clustering method, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise, a density-based spatial clustering algorithm) clustering method, a Mean Shift clustering method, a hierarchical clustering method, and the like.

[0080] As an embodiment, when the preset clustering method is the DBSCAN clustering method, the edge pixels are clustered according to the relationship between the edge pixels through the preset clustering method to obtain cluster cluster information, including: obtaining a preset neighborhood radius and a preset minimum number of points, wherein the preset neighborhood radius and the preset minimum number of points are set by the user on demand or according to experience; for each edge pixel, if the number of points contained in the neighborhood composed of the edge pixel point and the preset neighborhood radius is greater than or equal to the preset minimum number of points, the edge pixel point and the points in the neighborhood are determined as a preset cluster, and if the number of points contained in the neighborhood composed of the edge pixel point and the preset neighborhood radius is less than the preset minimum number of points, the edge pixel point is determined as a noise point.

[0081] Step 406 : Select target pixel points from edge pixel points according to the cluster information, and determine the target pixel points as edge point cloud data.

[0082] Among them, the clustering cluster information in step 406 is used to characterize the pixel point information contained in the clustering clusters of each pixel point type, and the pixel point types include a first type for characterizing the internal features of the bridge workpiece to be processed, a second type for characterizing the outer edge features of the bridge workpiece to be processed, and a third type for characterizing the inner edge features of the bridge workpiece to be processed.

[0083] Exemplarily, step 406 includes: determining the number of pixel points contained in the clusters belonging to each pixel point type based on the cluster information; selecting the cluster belonging to the target pixel point type with the largest number of corresponding pixels from the clusters belonging to each pixel point type; determining the edge pixel points contained in the clusters belonging to the target pixel point type as target pixel points, and determining the target pixel points as edge point cloud data.

[0084] It can be understood that since the edge pixel points are obtained by edge screening through the above-mentioned workpiece grayscale image, the result obtained after clustering the edge pixel points may include cluster clusters belonging to the above-mentioned first type, cluster clusters belonging to the above-mentioned second type, and cluster clusters belonging to the above-mentioned third type. Therefore, the second type of cluster cluster used to characterize the outer edge characteristics of the bridge workpiece to be processed contains the largest number of edge pixel points. Therefore, by screening the cluster cluster with the largest number of corresponding pixels, the edge point cloud data characterizing the outer edge characteristics of the bridge workpiece to be processed can be obtained.

[0085] In this embodiment, the workpiece point cloud data is mapped into a workpiece grayscale image, and each pixel in the workpiece grayscale image is traversed to select edge pixel points from each pixel in the workpiece grayscale image; the edge pixel points are clustered to obtain cluster cluster information; according to the cluster cluster information, target pixel points are selected from the edge pixel points, and the target pixel points are determined as edge point cloud data, and the pixel points are preliminarily screened for edges through the workpiece grayscale image, and further clustering processing and pixel number screening are performed to accurately screen and obtain edge point cloud data for characterizing the outer edge characteristics of the bridge workpiece to be processed, thereby improving the accuracy of edge point cloud data extraction.

[0086] In order to ensure the machining accuracy of the bridge workpiece, a method for accurately constructing the machining trajectory is required. In an exemplary embodiment, Figure 6 As shown, Figure 2 In step 206, a processing trajectory corresponding to the bridge workpiece to be processed is constructed according to the edge point cloud data, including:

[0087] Step 502 , sorting the edge point cloud data to obtain a point cloud sorting result, and dividing the edge point cloud data into at least one trajectory planning data group according to the point cloud sorting result.

[0088] Exemplarily, the edge point cloud data are sorted to obtain a point cloud sorting result, including: sorting the edge point cloud data according to the relative positions between the edge point cloud data to obtain a point cloud sorting result.

[0089] It is understandable that conventional point cloud sorting is usually sorted from left to right and from top to bottom. However, since the processing shape of the bridge workpiece to be processed may be an irregular shape, when processing the bridge workpiece to be processed, it is necessary to connect the end to the end according to the processing shape to obtain a processing trajectory. If the point cloud sorting result obtained by conventional point cloud sorting is used to generate a processing trajectory, it may be impossible to process the bridge workpiece to be processed normally, resulting in low accuracy in generating the processing trajectory, that is, low accuracy in processing the bridge workpiece.

[0090] In order to overcome the above-mentioned technical defect that the processing trajectory generated by the conventional point cloud sorting method from left to right and from top to bottom may not be able to normally process the bridge workpiece to be processed, resulting in low accuracy in generating the processing trajectory, that is, low processing accuracy of the bridge workpiece, as an embodiment, the edge point cloud data are sorted according to the relative position between the edge point cloud data to obtain the point cloud sorting result, including: determining any point cloud data in the edge point cloud data as the first edge point cloud data; determining the point cloud data closest to the first edge point cloud data as the next edge point cloud data corresponding to the first edge point cloud data; for each sorted edge point cloud data, determining the unsorted edge point cloud data closest to the sorted edge point cloud data as the next edge point cloud data of the sorted edge point cloud data, until the sorted edge point cloud data does not exist with the sorted edge point cloud data, then the point cloud sorting result is obtained.

[0091] In this way, through the above-mentioned sorting method, the point cloud sorting result can accurately describe the processing shape of the bridge workpiece to be processed, and the point cloud sorting result is one of the bases for generating the processing trajectory, so the accuracy of generating the processing trajectory is improved, that is, the processing accuracy of the bridge workpiece is improved.

[0092] Exemplarily, according to the point cloud sorting result, the edge point cloud data is divided into at least one trajectory planning data group, including: according to the point cloud sorting result, determining the point cloud shape composed between each edge point cloud data; according to the point cloud shape composed between each edge point cloud data, dividing the edge point cloud data into at least one trajectory planning data group.

[0093] Furthermore, according to the point cloud shape composed of each edge point cloud data, the edge point cloud data is divided into at least one trajectory planning data group, including: dividing the edge point cloud data corresponding to the same point cloud shape into a trajectory planning data group; or dividing the edge point cloud data corresponding to a regular point cloud shape into a trajectory planning data group; for example, the edge point cloud data corresponding to an arc shape is divided into a trajectory planning data group, and the edge point cloud data corresponding to a regular semi-closed rectangular shape is divided into a trajectory planning data group.

[0094] Step 504 : for each trajectory planning data set in the at least one trajectory planning data set, construct an initial trajectory according to the trajectory planning data set.

[0095] Exemplarily, step 504 includes: arbitrarily selecting a preset number of control points from the trajectory planning data group, and constructing a node vector according to the preset number of control points; constructing a basis function according to the node vector and the control points; obtaining a weight coefficient, a curve order and a control parameter of each control point; and constructing an initial trajectory according to the basis function, the position information of each control point, the weight coefficient, the curve order and the control parameter of each control point.

[0096] The initial trajectory can be a NURBS (Non-Uniform Rational B-Splines) curve. The weight coefficient is used to characterize the degree of deviation between the initial trajectory obtained by fitting and the control point. The initial trajectory can be pushed away from the control point by reducing the weight coefficient of the control point, and the initial trajectory can be pulled toward the control point by increasing the weight coefficient of the control point.

[0097] Among them, the node vector can be determined by a preset node vector calculation method, which includes but is not limited to a basic method based on the number of control points, an AVG (average) + KTP method (calculating the node vector based on control point parameters (usually normalized parameter values ​​on a parameterized curve)), a UAVG method (a more complex averaging or weighted averaging strategy based on control point parameters) and a custom method, etc.

[0098] As an embodiment, a node vector is constructed according to a preset number of control points, including: constructing a first vector whose number is the order of the curve, and constructing a second vector whose number is the sum of the order of the curve and the preset number of control points minus 1, and concatenating the first vector and the second vector to obtain a node vector, wherein a first vector value of the first vector is usually 0, and a second vector value of the second vector is usually a value in the interval (0, 1).

[0099] Furthermore, an initial trajectory is constructed according to the basis function, the position information of each control point, the weight coefficient of each control point, the curve order and the control parameters, including: the position information includes coordinates, the sum of the product of the function calculation value of the basis function corresponding to each control point, the weight coefficient of each control point and the coordinate of each control point is determined as the first curve parameter, the sum of the product of the function calculation value of the basis function corresponding to each control point and the weight coefficient of each control point is determined as the second curve parameter, and the ratio between the first curve parameter and the second curve parameter is determined as the trajectory equation corresponding to the initial trajectory.

[0100] Optionally, the ratio between the first curve parameter and the second curve parameter is determined as the trajectory equation corresponding to the initial trajectory, which can be expressed as follows:

[0101]

[0102] in, Determined by the preset number of control points, which is 1 less than the preset number of control points. For the The weight coefficient of the control point, For the The function calculation value of the basis function corresponding to the control point, For the The coordinates of the control points.

[0103] Step 506 , optimizing the initial trajectory according to the degree of fit between the initial trajectory and the trajectory planning data set to obtain an optimized trajectory.

[0104] Exemplarily, step 506 includes: obtaining a degree of fit between the initial trajectory and the trajectory planning data group; when the degree of fit is lower than a preset degree threshold, optimizing the initial trajectory to obtain an optimized trajectory; when the degree of fit is not lower than a preset degree threshold, determining the initial trajectory as the optimized trajectory, wherein the preset degree threshold is a preset critical value of the degree of fit requirement between the initial trajectory and the trajectory planning data group.

[0105] As an embodiment, obtaining the degree of fit between the initial trajectory and the trajectory planning data group includes: obtaining the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group; generating the degree of fit between the initial trajectory and the trajectory planning data group according to the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group.

[0106] Furthermore, according to the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group, the degree of fit between the initial trajectory and the trajectory planning data group is generated, including: integrating the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group to obtain the integrated distance between the initial trajectory and each edge point cloud data in the trajectory planning data group, and generating the degree of fit between the initial trajectory and the trajectory planning data group according to the integrated distance, wherein the shorter the integrated distance, the higher the degree of fit.

[0107] Among them, the distances between the initial trajectory and each edge point cloud data in the trajectory planning data group are integrated to obtain the integrated distance between the initial trajectory and each edge point cloud data in the trajectory planning data group. Specifically, the average value or sum of the distances between the initial trajectory and each edge point cloud data in the trajectory planning data group is determined as the integrated distance between the initial trajectory and each edge point cloud data in the trajectory planning data group.

[0108] Step 508, splicing the optimized trajectories corresponding to all trajectory planning data groups to obtain the processing trajectory corresponding to the bridge workpiece to be processed.

[0109] Exemplarily, according to the point cloud sorting result, the optimized trajectories corresponding to all trajectory planning data groups are spliced ​​head to tail in sequence to obtain the processing trajectory corresponding to the bridge workpiece to be processed.

[0110] It is understandable that when the robot arm is processing the bridge workpiece according to the processing trajectory, there is a possibility that the robot arm collides with surrounding obstacles and causes damage. Therefore, it is necessary to detect the circumference of the processing trajectory to avoid the robot arm colliding with surrounding obstacles and causing damage, thereby improving the processing safety of the robot arm.

[0111] In order to avoid the technical defect of the above-mentioned situation where the robot arm collides with surrounding obstacles and causes damage, as an embodiment, after step 508, it also includes: determining the trajectory circumference of the processing trajectory, if the trajectory circumference is greater than a preset circumference threshold, determining that the processing trajectory is an unsafe trajectory; if the trajectory circumference is not greater than the preset circumference threshold, determining that the processing trajectory is a safe trajectory, and sending the processing trajectory to the robot arm, so that the robot arm processes the bridge workpiece to be processed according to the processing trajectory, wherein the trajectory circumference of the processing trajectory is the product of the sampling density of the processing trajectory and the number of trajectory points.

[0112] In this way, the size of the trajectory circumference of the processing trajectory is judged. When the trajectory circumference is large, the risk of the robot arm colliding with surrounding obstacles is large, and the processing trajectory is determined to be an unsafe trajectory, so that the staff can be instructed to correct the processing trajectory. When the trajectory circumference is small, the risk of the robot arm colliding with surrounding obstacles is small, and the processing trajectory is determined to be a safe trajectory. The processing trajectory is sent to the robot arm for the robot arm to process the bridge workpiece to be processed according to the processing trajectory, thereby ensuring the processing safety of the robot arm.

[0113] In this embodiment, the edge point cloud data is sorted to obtain a point cloud sorting result, and the edge point cloud data is divided into at least one trajectory planning data group according to the point cloud sorting result; for each trajectory planning data group in the at least one trajectory planning data group, an initial trajectory is constructed according to the trajectory planning data group; according to the degree of fit between the initial trajectory and the trajectory planning data group, the initial trajectory is optimized to obtain an optimized trajectory; the optimized trajectories corresponding to all trajectory planning data groups are spliced ​​to obtain a processing trajectory corresponding to the bridge workpiece to be processed, and the edge point cloud data is segmentedly fitted according to the point cloud sorting, and the initial trajectory is optimized according to the degree of fit between the initial trajectory and the trajectory planning data group, so as to ensure that the processing trajectory obtained by splicing the optimized trajectory has a better fit with the edge point cloud data, thereby improving the accuracy of generating the processing trajectory.

[0114] In a more detailed embodiment, firstly, a workpiece image carrying the features of the bridge workpiece to be processed is obtained, and the region in the workpiece image used to characterize the features of the bridge workpiece to be processed is subjected to attribute filtering to obtain a regional image; the regional image is converted into a filtered image according to the conversion relationship between the image coordinate system and the robot arm coordinate system; point cloud data is extracted from the filtered image, and a spatial plane equation is constructed according to the point cloud data; the point cloud data is screened according to the flatness information and spatial plane equation corresponding to the bridge workpiece to be processed to obtain the workpiece point cloud data. The workpiece point cloud data is mapped into a workpiece grayscale image, and each pixel point in the workpiece grayscale image is traversed to select edge pixel points from each pixel point in the workpiece grayscale image; the edge pixel points are clustered to obtain cluster cluster information; according to the cluster cluster information, a target pixel point is selected from the edge pixel points, and the target pixel point is determined as the edge point cloud data.

[0115] Furthermore, the edge point cloud data are sorted to obtain a point cloud sorting result, and the edge point cloud data are divided into at least one trajectory planning data group according to the point cloud sorting result; for each trajectory planning data group in the at least one trajectory planning data group, an initial trajectory is constructed according to the trajectory planning data group; the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group is obtained; the degree of fit between the initial trajectory and the trajectory planning data group is generated according to the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group; according to the degree of fit, the initial trajectory is optimized to obtain an optimized trajectory; the optimized trajectories corresponding to all trajectory planning data groups are spliced ​​to obtain a processing trajectory corresponding to the bridge workpiece to be processed.

[0116] In this way, a filtered image is obtained by performing attribute filtering processing on the workpiece image; point cloud data is extracted from the filtered image, and a spatial plane equation is constructed based on the point cloud data; the point cloud data is screened according to the flatness information and spatial plane equation corresponding to the bridge workpiece to be processed to obtain workpiece point cloud data, and a filtered image that can characterize the shape of the bridge workpiece to be processed is obtained through attribute filtering processing, and a spatial plane equation that can characterize the shape of the bridge workpiece to be processed is further constructed, and then based on the flatness information and the spatial plane equation, the workpiece point cloud data that can accurately characterize the appearance characteristics of the bridge workpiece to be processed is finally obtained, thereby improving the accuracy of the extraction of the workpiece point cloud data.

[0117] Furthermore, by mapping the workpiece point cloud data into a workpiece grayscale image, and traversing each pixel point in the workpiece grayscale image, edge pixel points are selected from each pixel point in the workpiece grayscale image; the edge pixel points are clustered to obtain cluster cluster information; according to the cluster cluster information, target pixel points are selected from the edge pixel points, and the target pixel points are determined as edge point cloud data, and the pixel points are preliminarily screened for edges through the workpiece grayscale image, and further clustering processing and pixel number screening are performed, so that edge point cloud data for characterizing the outer edge characteristics of the bridge workpiece to be processed can be accurately screened, thereby improving the accuracy of edge point cloud data extraction.

[0118] Furthermore, by sorting the edge point cloud data, a point cloud sorting result is obtained, and according to the point cloud sorting result, the edge point cloud data is divided into at least one trajectory planning data group; for each trajectory planning data group in the at least one trajectory planning data group, an initial trajectory is constructed according to the trajectory planning data group; according to the degree of fit between the initial trajectory and the trajectory planning data group, the initial trajectory is optimized to obtain an optimized trajectory; the optimized trajectories corresponding to all trajectory planning data groups are spliced ​​to obtain a processing trajectory corresponding to the bridge workpiece to be processed, and segmented trajectory fitting is performed on the edge point cloud data according to the point cloud sorting, and according to the degree of fit between the initial trajectory and the trajectory planning data group, the initial trajectory is optimized, thereby ensuring that the processing trajectory obtained by splicing the optimized trajectory has a better fit with the edge point cloud data, thereby improving the accuracy of generating the processing trajectory.

[0119] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0120] Based on the same inventive concept, the embodiment of the present application also provides a bridge workpiece machining trajectory generation device for implementing the bridge workpiece machining trajectory generation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the bridge workpiece machining trajectory generation device provided below can refer to the limitations of the bridge workpiece machining trajectory generation method above, and will not be repeated here.

[0121] In an exemplary embodiment, Figure 7 As shown, a bridge workpiece machining trajectory generating device 700 is provided, comprising: an extraction module 702, a screening module 704 and a construction module 706, wherein:

[0122] An extraction module 702 is used to obtain a workpiece image carrying features of the bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image;

[0123] A screening module 704 is used to screen the workpiece edge of the workpiece point cloud data to obtain edge point cloud data;

[0124] The construction module 706 is used to construct a processing trajectory corresponding to the bridge workpiece to be processed according to the edge point cloud data.

[0125] In one of the embodiments, the extraction module 702 is also used to perform attribute filtering on the workpiece image to obtain a filtered image; extract point cloud data from the filtered image, and construct a spatial plane equation based on the point cloud data; filter the point cloud data according to the flatness information and spatial plane equation corresponding to the bridge workpiece to be processed to obtain workpiece point cloud data.

[0126] In one embodiment, the extraction module 702 is also used to perform attribute filtering on the area in the workpiece image used to characterize the characteristics of the bridge workpiece to be processed to obtain a regional image; and convert the regional image into a filtered image based on the conversion relationship between the image coordinate system and the robot arm coordinate system.

[0127] In one of the embodiments, the screening module 704 is also used to map the workpiece point cloud data into a workpiece grayscale image, and traverse each pixel point in the workpiece grayscale image, select edge pixel points from each pixel point in the workpiece grayscale image; cluster the edge pixel points to obtain cluster cluster information; select target pixel points from the edge pixel points based on the cluster cluster information, and determine the target pixel points as edge point cloud data.

[0128] In one of the embodiments, the construction module 706 is also used to sort the edge point cloud data to obtain a point cloud sorting result, and divide the edge point cloud data into at least one trajectory planning data group according to the point cloud sorting result; for each trajectory planning data group in the at least one trajectory planning data group, an initial trajectory is constructed according to the trajectory planning data group; according to the degree of fit between the initial trajectory and the trajectory planning data group, the initial trajectory is optimized to obtain an optimized trajectory; and the optimized trajectories corresponding to all trajectory planning data groups are spliced ​​to obtain a processing trajectory corresponding to the bridge workpiece to be processed.

[0129] In one embodiment, the construction module 706 is also used to obtain the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group; generate the degree of fit between the initial trajectory and the trajectory planning data group according to the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group; and optimize the initial trajectory according to the degree of fit to obtain an optimized trajectory.

[0130] Each module in the above-mentioned bridge workpiece machining trajectory generation device can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

[0131] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for generating a machining trajectory of a bridge workpiece is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0132] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0134] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0135] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0136] It should be noted that the image information involved in this application (including but not limited to the target image, the first training sample, the second training sample, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0137] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0138] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0139] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a machining trajectory of a bridge workpiece, characterized in that: The method comprises: Acquire a workpiece image carrying features of a bridge workpiece to be processed, and extract workpiece point cloud data from the workpiece image; Performing workpiece edge screening on the workpiece point cloud data to obtain edge point cloud data; A processing trajectory corresponding to the bridge workpiece to be processed is constructed based on the edge point cloud data.

2. The method according to claim 1, characterized in that The step of extracting workpiece point cloud data from the workpiece image comprises: Performing attribute filtering on the workpiece image to obtain a filtered image; Extracting point cloud data from the filtered image, and constructing a spatial plane equation based on the point cloud data; According to the flatness information corresponding to the bridge workpiece to be processed and the spatial plane equation, the point cloud data is screened to obtain the workpiece point cloud data.

3. The method according to claim 2, characterized in that The performing attribute filtering on the workpiece image to obtain a filtered image includes: Performing attribute filtering on a region in the workpiece image used to characterize the features of the bridge workpiece to be processed to obtain a regional image; The regional image is converted into a filtered image according to the conversion relationship between the image coordinate system and the robot arm coordinate system.

4. The method according to claim 1, characterized in that: The step of screening the workpiece edge of the workpiece point cloud data to obtain edge point cloud data includes: Mapping the workpiece point cloud data into a workpiece grayscale image, traversing each pixel point in the workpiece grayscale image, and selecting edge pixel points from each pixel point in the workpiece grayscale image; Performing clustering processing on the edge pixels to obtain cluster information; According to the cluster information, target pixels are selected from the edge pixels, and the target pixels are determined as edge point cloud data.

5. The method according to claim 1, characterized in that The step of constructing a processing trajectory corresponding to the bridge workpiece to be processed according to the edge point cloud data includes: Sorting the edge point cloud data to obtain a point cloud sorting result, and dividing the edge point cloud data into at least one trajectory planning data group according to the point cloud sorting result; For each trajectory planning data set in the at least one trajectory planning data set, constructing an initial trajectory according to the trajectory planning data set; According to the degree of fit between the initial trajectory and the trajectory planning data group, the initial trajectory is optimized to obtain an optimized trajectory; The optimized trajectories corresponding to all the trajectory planning data groups are spliced ​​together to obtain a processing trajectory corresponding to the bridge workpiece to be processed.

6. The method according to claim 5, characterized in that The step of optimizing the initial trajectory according to the degree of fit between the initial trajectory and the trajectory planning data set to obtain an optimized trajectory comprises: Obtaining the distance between the initial trajectory and each edge point cloud data in the trajectory planning data group; Generate a fitting degree between the initial trajectory and the trajectory planning data set according to the distance between the initial trajectory and each edge point cloud data in the trajectory planning data set; According to the degree of fitting, the initial trajectory is optimized to obtain an optimized trajectory.

7. A bridge workpiece machining trajectory generating device, characterized in that: The bridge workpiece machining trajectory generating device comprises: An extraction module, used for acquiring a workpiece image carrying features of a bridge workpiece to be processed, and extracting workpiece point cloud data from the workpiece image; A screening module, used for screening the workpiece edge of the workpiece point cloud data to obtain edge point cloud data; A construction module is used to construct a processing trajectory corresponding to the bridge workpiece to be processed based on the edge point cloud data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Bridge crack calibration method and device based on computer vision

    CN120198512A

  • Bridge crack calibration method and device based on computer vision

    CN120198512B