Linear welding seam identification method and device

Abstract

The invention provides a linear welding seam recognition method and device, and relates to the technical field of computers. The method comprises the following steps: according to a plane equation of a first initial plane and a second initial plane obtained by performing plane detection on a to-be-identified point cloud, calculating to obtain a first intersecting line; according to the distribution condition of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the to-be-identified point cloud, determining a line section from the first intersecting line as an initial welding line; and for each initial end point of each initial welding seam, according to a local plane in the local point cloud corresponding to the initial end point in the to-be-identified point cloud, the initial end point is adjusted to obtain a target end point corresponding to the initial end point, and two target end points corresponding to one initial welding seam are two end points of one target welding seam. In this way, local point position adjustment is conducted on the two end points, determined based on the plane intersecting line, of the initial welding seam, and therefore the more accurate linear welding seam position is obtained.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for recognizing a linear weld. Background Art

[0002] Compared with manual welding, welding robots have the characteristics of high efficiency and high precision. Therefore, with the development of science and technology, robot welding has been gradually and widely used in various fields. In order to ensure the welding quality of the welding robot when performing straight welds, it is necessary to accurately obtain the starting and ending positions of the straight welds. Therefore, how to improve the accuracy of the detected straight welds has become a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0003] The purpose of the present application includes, for example, providing a linear weld identification method, apparatus, computer equipment and readable storage medium, which obtains a more accurate linear weld position by locally adjusting the two end points of the initial weld determined based on the plane intersection line.

[0004] The embodiments of the present application can be implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a linear weld recognition method, the method comprising:

[0006] Calculate a first intersection line according to the plane equations of the first initial plane and the second initial plane obtained by plane detection of the point cloud to be identified;

[0007] According to the distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified, determining a line segment from the first intersection line as an initial weld;

[0008] For each initial endpoint of each initial weld, the initial endpoint is adjusted according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified to obtain the target endpoint corresponding to the initial endpoint, wherein the two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a straight line weld.

[0009] In a second aspect, an embodiment of the present application provides a linear weld recognition device, the device comprising:

[0010] A calculation module, used for calculating a first intersection line according to plane equations of a first initial plane and a second initial plane obtained by plane detection on the point cloud to be identified;

[0011] a detection module, configured to determine a line segment from the first intersection line as an initial weld according to distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified;

[0012] The local point adjustment module is used to adjust each initial endpoint of each initial weld according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified, so as to obtain the target endpoint corresponding to the initial endpoint, wherein the two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a straight weld.

[0013] In a third aspect, an embodiment of the present application provides a computer device, including a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the linear weld identification method described in the aforementioned embodiment.

[0014] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the linear weld recognition method as described in the aforementioned embodiment is implemented.

[0015] The linear weld recognition method, device, computer equipment and readable storage medium provided by the embodiment of the present application first calculate the first intersection line according to the equations of the two initial planes obtained by plane detection of the point cloud to be identified; then, according to the distribution of the points in the point cloud corresponding to each of the two initial planes in the point cloud to be identified, determine the line segment as the initial weld from the determined first intersection line; finally, for each initial weld, for each of the two initial endpoints of the initial weld, according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified, the initial endpoint is adjusted, and the obtained point is used as the target endpoint corresponding to the initial endpoint, wherein the two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a linear weld. In this way, by adjusting the local point positions of the two endpoints of the initial weld determined based on the plane intersection line, a more accurate linear weld position is obtained, which can avoid the situation that the initial weld is offset more than the actual linear weld when the initial weld is directly used as the linear weld to be identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A block diagram of a computer device provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of a flow chart of a linear weld identification method provided in an embodiment of the present application;

[0019] Figure 3 A schematic diagram of line segment offset provided in an embodiment of the present application;

[0020] Figure 4 for Figure 2 A schematic flow chart of the sub-steps included in step S200;

[0021] Figure 5 for Figure 4 A schematic flow chart of the sub-steps included in sub-step S230;

[0022] Figure 6 for Figure 2 A schematic flow chart of the sub-steps included in step S300;

[0023] Figure 7 for Figure 6 A schematic flow chart of the sub-steps included in sub-step S310;

[0024] Figure 8 A schematic diagram of a cylinder based on two reference points provided in an embodiment of the present application;

[0025] Fig. 9 for Figure 6 A schematic flow chart of the sub-steps included in sub-step S330;

[0026] Fig.10 for Fig. 9 A schematic flow chart of the sub-steps included in sub-step S332;

[0027] Fig.11 A block diagram of a linear weld identification device provided in an embodiment of the present application.

[0028] Icons: 100 - computer equipment; 110 - memory; 120 - processor; 130 - communication unit; 200 - straight weld identification device; 210 - calculation module; 220 - detection module; 230 - local point adjustment module. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0030] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0031] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0032] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0033] Please refer to Figure 1 , Figure 1 A block diagram of a computer device 100 provided in an embodiment of the present application. The computer device 100 may be, but is not limited to, a computer, a server, a welding robot, etc. The computer device 100 includes a memory 110, a processor 120, and a communication unit 130. The memory 110, the processor 120, and the communication unit 130 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines.

[0034] The memory 110 is used to store programs or data. The memory 110 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0035] The processor 120 is used to read / write data or programs stored in the memory 110 and execute corresponding functions. For example, the memory 110 stores a linear weld recognition device 200, and the linear weld recognition device 200 includes at least one software function module that can be stored in the memory 110 in the form of software or firmware. The processor 120 executes various functional applications and data processing by running software programs and modules stored in the memory 110, such as the linear weld recognition device 200 in the embodiment of the present application, that is, realizing the linear weld recognition method in the embodiment of the present application.

[0036] The communication unit 130 is used to establish a communication connection between the computer device 100 and other communication terminals through a network, and to send and receive data through the network.

[0037] It should be understood that Figure 1 The structure shown is only a schematic diagram of the structure of the computer device 100. The computer device 100 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0038] Please refer to Figure 2 , Figure 2 The schematic diagram of the process flow of the linear weld recognition method provided in the embodiment of the present application. The method can be applied to the above-mentioned computer device. The specific process flow of the linear weld recognition method is described in detail below. In this embodiment, the method can include steps S100 to S300.

[0039] Step S100, calculating a first intersection line according to plane equations of a first initial plane and a second initial plane obtained by plane detection on the point cloud to be identified.

[0040] In this embodiment, the point cloud to be identified is a point cloud corresponding to a scene where a straight weld needs to be identified. For example, if a straight weld on a workpiece needs to be identified for automatic welding, the point cloud of the workpiece can be collected as the point cloud to be identified. It can be understood that the points in the point cloud to be identified are three-dimensional points.

[0041] The plane equation of the first initial plane and the plane equation of the second initial plane can be obtained, and then the equation of the first intersection line of the first initial plane and the second initial plane can be calculated according to the above two plane equations. In this way, the first intersection line can be determined. It can be understood that the first intersection line is the plane intersection line of the first initial plane and the second initial plane, and the first intersection line is a straight line.

[0042] Among them, the plane equation of the first initial plane and the plane equation of the second initial plane can be obtained by other devices performing plane detection on the point cloud to be identified and sent to the computer device, or can be obtained by the computer device performing plane detection on the point cloud to be identified. That is, the first initial plane and the second initial plane are planes obtained by plane detection on the point cloud to be identified. The plane detection method used can be, but is not limited to, the Random Hough Transform (RHT) algorithm, the random sample consensus (RANSAC) algorithm, the deterministic voting algorithm, etc., which can be determined in combination with actual needs and are not specifically limited here. The first initial plane and the second initial plane are two planes that intersect based on the normal vectors of the planes. There may be more than two planes detected from the point cloud to be identified. When more than two planes are detected, the specific method of determining the first initial plane and the second initial plane from more than two planes can be set in combination with actual needs.

[0043] Step S200: determining a line segment from the first intersection line as an initial weld according to the distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified.

[0044] Since the first intersection line is an infinitely long straight line, and welding requires a starting and ending point, a line segment can be determined from the first intersection line as the initial weld. In order to reduce the misidentification of straight welds, a line segment can be determined from the first intersection line as the initial weld according to the distribution of points in the first point cloud and the distribution of points in the second point cloud. The first point cloud is the point cloud corresponding to the first initial plane in the point cloud to be identified, that is, the points in the first point cloud are the point clouds belonging to the first initial plane in the point cloud to be identified; the second point cloud is the point cloud corresponding to the second initial plane in the point cloud to be identified, that is, the points in the second point cloud are the point clouds corresponding to the second initial plane in the point cloud to be identified.

[0045] By determining the initial weld according to the distribution of points in the first point cloud and the second point cloud, it is possible to avoid taking the area on the first intersection line that does not correspond to the first point cloud and the second point cloud as part of the initial weld due to ignoring the distribution of the first point cloud and the second point cloud.

[0046] It is worth noting that the number of initial welds determined on the first intersection line may be 0, 1, or multiple, depending on the actual situation.

[0047] The inventor of the present application has found through research that when finding the intersection of the planes obtained by the plane detection algorithm and then determining the line segment on the intersection as the initial weld, the determined initial weld will be offset compared to the real straight weld, that is, the initial weld will not completely overlap with the actual weld. Figure 3 As shown in the figure, line segment 1 represents the initial weld obtained based on the detected plane, and line segment 2 is the actual weld. It can be seen that the left end of line segment 1 is offset downward compared with the left end of line segment 2; and the right end of line segment 1 is offset upward compared with the right end of line segment 2 (i.e., the actual weld). The reason for this is that since the point cloud generally contains a little noise, when the plane of the actual object (e.g., the actual workpiece) constituting the straight weld has a large area, the object plane cannot actually be represented by a single plane equation. The plane obtained by detecting the point cloud to be detected using the plane detection algorithm is only an average plane of the actual object plane. The average plane does not completely coincide with the actual object plane at the weld position. Therefore, the initial weld determined directly on the intersection of the average plane will not match the actual weld.

[0048] Step S300, for each initial endpoint of each initial weld, the initial endpoint is adjusted according to a local plane in a local point cloud corresponding to the initial endpoint in the point cloud to be identified, so as to obtain a target endpoint corresponding to the initial endpoint.

[0049] In order to alleviate the situation where the initial weld is offset from the actual weld, when the initial weld is determined, local point adjustments can be made for each determined initial weld to reduce the offset from the actual weld. In this embodiment, for each initial weld, for each of the two initial endpoints of the initial weld, the initial endpoint can be adjusted according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified, and the adjusted point is used as the target endpoint corresponding to the initial endpoint, so that two target endpoints corresponding to an initial weld can be obtained, and the two target endpoints are the two endpoints of a target weld, and the target weld is a straight weld. In this way, by adjusting the two endpoints of the initial weld determined based on the plane intersection, a more accurate straight weld position can be obtained. Among them, the two target endpoints of a target weld are the starting point and end point of the target weld.

[0050] The initial endpoints are the endpoints of the initial weld, and the two initial endpoints of an initial weld are the starting point and the end point of the initial weld. The local point cloud corresponding to an initial endpoint is the point cloud located near the initial endpoint in the point cloud to be identified, and the local point cloud corresponding to an initial endpoint includes the initial endpoint. The specific determination method can be determined in combination with actual needs.

[0051] As a possible implementation, a first detection result can be obtained by performing plane detection on the point cloud to be identified, and the first detection result includes the plane detected from the point cloud to be identified. The planes in the first detection result can be combined, and based on the normal vectors of the planes in each plane combination, it can be determined whether two planes in each plane combination intersect, and when the intersection is determined, the two planes in the plane combination are used as the first initial plane and the second initial plane in step S100 to obtain the corresponding initial weld, and then the two end points of the initial weld are locally adjusted to obtain the target weld corresponding to the initial weld. The offset initial weld can be corrected by local point adjustment to obtain a target weld with a high degree of fit with the actual weld. In this way, the straight weld (i.e., the target weld) in the point cloud to be identified can be detected.

[0052] For example, the variable i is used to traverse the planes in the first detection result, and the value range of i is 1≤i<the number of planes in the first detection result-1; the variable j is used to traverse the planes in the first detection result, and the value range of j is 1+i≤j<the number of planes in the first detection result. For all combinations of i and j, the plane intersection line is calculated, and then the initial weld is calculated on the obtained plane intersection line.

[0053] Among them, when it is necessary to identify all target welds in the point cloud to be identified, after the processing of determining the initial welds is performed based on all plane combinations, all the determined initial welds can be traversed, and the traversed initial welds can be adjusted locally to obtain the target welds; or after obtaining the initial weld corresponding to a plane combination, the initial weld can be adjusted locally, and then the next plane combination can be processed. The specific execution order can be determined in combination with actual needs and is not specifically limited here.

[0054] As a possible implementation, Figure 4 The method shown determines the initial weld from a first intersection line. Figure 4 , Figure 4 for Figure 2 Schematic diagram of the flow of sub-steps included in step S200. In this embodiment, step S200 may include sub-steps S210 to S230.

[0055] In sub-step S210, for the first point cloud, all points in the first point cloud that are near the first intersection line are projected onto the first intersection line, and without determining the number of clusters, the obtained first projection points are clustered to obtain at least one first projection point set.

[0056] Sub-step S220, for the second point cloud, project all points in the second point cloud located near the first intersection line onto the first intersection line, and cluster the obtained second projection points without determining the number of clusters to obtain at least one second projection point set.

[0057] Sub-step S230, analyzing whether there is an intersection between the first line segment intervals corresponding to each of the first projection point sets and the second line segment intervals corresponding to each of the second projection point sets, and if there is an intersection, determining the initial weld according to the existing intersection.

[0058] In this embodiment, for each point in the first point cloud, a third distance between the point and the first intersection line can be calculated, and it is determined whether the third distance is less than a second preset distance; if less than, the point is regarded as a point in the first point cloud located near the first intersection line; if not less than, the point is not regarded as a point in the first point cloud located near the first intersection line. For each point in the first point cloud located near the first intersection line, the point is projected onto the first intersection line to obtain a first projection point.

[0059] Similarly, for each point in the second point cloud, the fourth distance between the point and the first intersection line can be calculated, and it is determined whether the fourth distance is less than the second preset distance; if it is less than, the point is regarded as a point in the second point cloud located near the first intersection line; if it is not less than, the point is not regarded as a point in the second point cloud located near the first intersection line. For each point in the second point cloud located near the first intersection line, the point is projected onto the first intersection line to obtain a second projection point.

[0060] As a possible implementation method, without determining the number of clustering categories, all first projection points and all second projection points can be directly clustered, and clustering results corresponding to all first projection points and clustering results corresponding to all second projection points can be obtained. Among them, each cluster in the clustering results corresponding to all first projection points corresponds to a first projection point set, and each cluster in the clustering results corresponding to all second projection points corresponds to a second projection point set. The clustering method used can be, but is not limited to, Euclidean clustering, etc. The Euclidean clustering algorithm does not need to pre-specify the number of clusters.

[0061] As another possible implementation, the first number of all first projection points and the second number of all second projection points can be firstly obtained by counting. Then, it is determined whether the first number and the second number are both greater than the preset number. If so, a cluster analysis can be performed to obtain at least one first projection point set and at least one second projection point set; if not, the initial weld determined from the first intersection line can be directly determined to be 0, that is, the initial weld cannot be determined on the first intersection line, in which case step S300 can be no longer performed. Among them, the preset number can be 0 or greater than 0, which can be determined in combination with actual conditions. In this way, unnecessary calculations can be reduced.

[0062] The first projection point and the second projection point are both located on the first intersection line. Therefore, a corresponding first line segment interval can be determined according to each first projection point set, and a corresponding second line segment interval can be determined according to each second projection point set. The first line segment interval corresponding to a projection point set is determined by the projection point set. For example, a projection point set includes point 1, point 2, point 3, and point 4. Points 1-4 are located on the first intersection line, and points 2-4 are located between point 1 and point 4. Then point 1 and point 4 can be used as the endpoints of the corresponding line segment interval, and the line segment interval represents a line segment with two end points of point 1 and point 4 on the first intersection line.

[0063] When each first line segment interval and each second line segment interval are determined, for each first line segment interval, it can be determined whether the first line segment interval and each second line segment interval have an intersection, and when it is determined that there is an intersection, the intersection is analyzed. It can be understood that the intersection represents the overlapping portion of a first line segment interval and a second line segment interval. When each intersection is determined, it can be determined whether there is a corresponding initial weld based on the intersection, and the corresponding initial weld can be determined sometimes; when all intersections are determined, the determined intersections can be traversed to determine whether the traversed intersection has a corresponding initial weld, and the corresponding initial weld can be determined sometimes.

[0064] Optionally, each intersection may be directly used as the corresponding initial weld.

[0065] Optionally, you can also Figure 5 The method shown determines the initial weld based on the intersection. Figure 5 , Figure 5 for Figure 4 Schematic diagram of the flow of sub-steps included in sub-step S230. In this embodiment, sub-step S230 may include sub-steps S231 to S234.

[0066] Sub-step S231, determining the nearest points corresponding to the two intersection endpoints of the intersection from the first point cloud and the second point cloud, and calculating the second distance between each intersection endpoint and the corresponding nearest point.

[0067] Sub-step S232, determining whether the obtained multiple second distances are all less than or equal to the first preset distance.

[0068] If the calculated second distances are all less than or equal to the first preset distance, sub-step S233 is executed.

[0069] Sub-step S233, taking the line segment indicated by the intersection as an initial weld.

[0070] If at least one second distance is greater than the first preset distance, sub-step S234 is executed.

[0071] Sub-step S234: Do not use the line segment indicated by the intersection as an initial weld.

[0072] In this embodiment, the intersection represents a line segment, and the endpoint of the intersection can be called an intersection endpoint. For an intersection, for each intersection endpoint of the intersection, the nearest point of the intersection endpoint can be determined from the first point cloud, and the distance between the intersection endpoint and the nearest point can be calculated as the second distance; and the nearest point of the intersection endpoint can be determined from the second point cloud, and the distance between the intersection endpoint and the nearest point can be calculated as the second distance. In this way, the corresponding four nearest points can be determined based on the two intersection endpoints of an intersection.

[0073] Determine whether the four second distances corresponding to the above four nearest points are all less than or equal to the first preset distance. If so, the line segment represented by the intersection can be used as an initial weld; if not, the line segment represented by the intersection is not used as an initial weld.

[0074] When at least one initial weld is determined in step S200, the at least one initial weld may be traversed to adjust the local position of each initial weld to obtain a corresponding target weld. Figure 6 The local point adjustment is performed in the manner shown. Figure 6 , Figure 6 for Figure 2 Schematic diagram of the flow of sub-steps included in step S300. In this embodiment, step S300 may include sub-steps S310 to S350.

[0075] Sub-step S310, for the initial endpoint, determining the local point cloud corresponding to the initial endpoint.

[0076] In this embodiment, based on the initial endpoint, a portion of the point cloud located near the initial endpoint can be determined from the point cloud to be identified as the local point cloud corresponding to the initial endpoint. Optionally, a bounding box can be set, and then the corresponding local point cloud can be determined from the point cloud to be identified based on the bounding box.

[0077] As a possible implementation, Figure 7 The local point cloud corresponding to an initial endpoint is determined in the manner shown. Figure 7 , Figure 7 for Figure 6 Schematic diagram of the flow of sub-steps included in sub-step S310. In this embodiment, sub-step S310 may include sub-steps S311 to S312.

[0078] Sub-step S311, determining a cylinder according to the initial endpoint and the initial weld where the initial endpoint is located.

[0079] Sub-step S312, using the determined cylinder to determine the local point cloud corresponding to the initial endpoint from the point cloud to be identified.

[0080] In this embodiment, the axis of the cylinder can be determined according to the initial endpoint and the initial weld where the initial endpoint is located, and a cylindrical bounding box can be determined in combination with a preset radius. The initial endpoint is located on the axis of the cylinder, and the axis of the cylinder is located on the corresponding first intersection line. After the cylinder is determined, the point cloud located in the cylinder in the point cloud to be identified can be used as the local point cloud corresponding to the initial endpoint.

[0081] As a possible implementation method, there is only one initial endpoint on the axis of the cylinder, that is, the two initial endpoints of an initial weld correspond to different local point clouds. This can prevent the poor adjustment effect caused by the local plane at the starting point and the local plane at the end point being not completely consistent.

[0082] As another possible implementation method, in order to speed up the adjustment speed, the axis of the cylinder has two initial endpoints of an initial weld, that is, the two initial endpoints of an initial weld respectively correspond to the same local point cloud. In this way, when a local point cloud is determined, the two initial endpoints of the initial weld can be adjusted using the local point cloud.

[0083] As another possible implementation, in order to ensure the adjustment effect and speed, it can be determined whether to use one local point cloud or two different local point clouds when adjusting the two initial endpoints of the initial weld according to the length of the current initial weld.

[0084] In this implementation, the weld length of the initial weld can be obtained first, and then it is determined whether the weld length of the initial weld is greater than the preset length. Wherein, the preset length can be set in combination with actual needs. If the weld length is greater than the preset length, it means that the length of the initial weld is longer, and the local planes at the two initial endpoints of the initial weld may not be completely consistent. In this case, for each of the two initial endpoints of the initial weld, a point can be determined on the initial weld as a target point, and then according to the preset radius, the initial endpoint, and the target point corresponding to the initial endpoint, the cylinder corresponding to the initial endpoint is determined, and then based on the cylinder corresponding to the initial endpoint, the local point cloud corresponding to the initial endpoint is determined from the point cloud to be identified. Wherein, the target point is located between the initial endpoint and the other initial endpoint of the initial weld where the initial endpoint is located. In this way, when the weld length is longer, the local point clouds corresponding to the two initial endpoints can be determined, and then the corresponding initial endpoints can be adjusted based on the local planes in the local point clouds corresponding to each initial endpoint.

[0085] If the weld length is less than or equal to the preset length, it means that the length of the initial weld is not very long, and the local planes at the two initial endpoints of the initial weld may be consistent. In this case, the corresponding cylinder can be determined according to the preset radius and the two initial endpoints of the initial weld, and then based on the cylinder, the same local point cloud corresponding to the two initial endpoints of the initial weld in the point cloud to be identified can be obtained. In this way, when the weld length is short, the two initial endpoints of an initial weld can be adjusted based on the same local point cloud.

[0086] Optionally, when two different local point clouds need to be determined for an initial weld, an initial endpoint can be used as the center of one bottom surface of the corresponding cylinder, and the target point corresponding to the initial endpoint can be used as the center of another bottom surface of the corresponding cylinder. Similarly, when only one local point cloud needs to be determined for an initial weld, an initial endpoint of the initial weld can be used as the center of one bottom surface of the corresponding cylinder, and the other initial endpoint of the initial weld can be used as the center of another bottom surface of the corresponding cylinder.

[0087] Optionally, two reference points can be set: p_in[0], p_in[1], where one reference point represents an initial endpoint of an initial weld, and the other reference point represents another initial weld or a target point of the initial weld. The reference point representing the initial endpoint can be adjusted a certain distance on the first intersection line in a direction away from the other initial endpoint of the initial weld, and the adjusted point is used as the center of a bottom surface of the corresponding cylinder, and the other reference point that has not been adjusted is used as the center of another bottom surface of the corresponding cylinder.

[0088] Optionally, you can Figure 8 As shown, the two reference points p_in[0] and p_in[1] are extended outward along the cylinder axis by a certain distance seg_l, and then the points obtained after extension are used as the centers of the upper and lower bases of the cylinder, and combined with the preset radius seg_r, the cylinder is determined.

[0089] Sub-step S320, performing plane detection on the local point cloud to obtain a second detection result.

[0090] Sub-step S330: determining two local planes as target planes from the second detection result.

[0091] In this embodiment, when a local point cloud is obtained, a plane detection may be performed on the local point cloud, and the obtained result may be used as a second detection result. The second detection result includes a local plane, and the local plane is a plane obtained by plane detection from the local point cloud. Two local planes may be determined from the second detection result as target planes, that is, two target planes are determined. Among them, one of the two target planes is similar to the first initial plane, and the other is similar to the second initial plane.

[0092] As a possible implementation, Fig. 9 The two target planes are selected in the manner described. Fig. 9 , Fig. 9 for Figure 6 Schematic diagram of the flow of sub-steps included in sub-step S330. In this embodiment, sub-step S330 may include sub-steps S331 to S333.

[0093] Sub-step S331, determining whether the number of local planes in the second detection result is greater than 2.

[0094] In this embodiment, the second detection result is obtained by detecting the local point cloud based on the initial endpoint, and the initial endpoint is a point near the actual intersection of two planes, so the second detection result includes at least two local planes. The number of local planes in the second detection result can be determined first. Then, it is determined whether the number of planes is greater than 2.

[0095] When the number of planes is greater than 2, sub-step S332 may be executed.

[0096] Sub-step S332, calculates the first similarity between each local plane and the first initial plane based on the plane information of each local plane in the second detection result and the plane information of the first initial plane, and selects the local plane corresponding to the largest first similarity as the selected first target plane; and, calculates the second similarity between each local plane and the second initial plane based on the plane information of each local plane and the plane information of the second initial plane, and selects the local plane corresponding to the largest second similarity as the selected second target plane.

[0097] In this embodiment, when there are more than two local planes in the second detection result, the plane information of the local planes, the plane information of the first initial plane, and the plane information of the second initial plane can be combined to calculate the first similarity between each local plane and the first initial plane, and the second similarity between each local plane and the second initial plane; then, the local plane corresponding to the largest first similarity is taken as the plane most similar to the first initial plane, that is, the local plane corresponding to the largest first similarity is taken as the selected first target plane. And, the local plane corresponding to the largest second similarity is taken as the plane with similarity to the second initial plane, that is, the local plane corresponding to the largest second similarity is taken as the selected second target plane. The above-mentioned first target plane and second target plane are the two target planes determined from the second detection result.

[0098] The plane information is used to describe the properties of the plane, as long as it can be used to calculate the similarity between planes. It can be understood that the plane described by the plane information is an infinite plane.

[0099] As a possible implementation, the plane information includes a normal vector n and a distance value ρ, wherein the distance value ρ represents the distance between the plane and the origin of the coordinate system, and the distance value has a positive and negative sign. The plane equation is: ax+by+cz+d=0, wherein a, b, and c are used to describe the normal vector n of the plane, and d=-ρ. The similarity between two planes is represented by a first distance. The greater the similarity, the smaller the first distance. The first distance can be expressed by Fig.10 Please refer to Fig.10 , Fig.10 for Fig. 9 Schematic diagram of the flow of sub-steps included in sub-step S332. In this embodiment, sub-step S332 may include sub-steps S3321 to S3323.

[0100] Sub-step S3321, calculating and obtaining the inner product value of the first normal vector and the second normal vector.

[0101] Sub-step S3322, obtaining an interval distance value according to a first distance value corresponding to the first plane and a second distance value corresponding to the second plane.

[0102] Sub-step S3323, calculate the product of the reciprocal of the inner product value and the interval distance value, and obtain the first distance according to the absolute value of the product.

[0103] In this embodiment, the two planes that need to calculate the similarity include a first plane and a second plane, the normal vector of the first plane is the first normal vector, the distance value of the first plane is the first distance value, the normal vector of the second plane is the second normal vector, and the distance value of the second plane is the second plane value. The inner product value of the first normal vector and the second normal vector can be calculated. And, the spacing distance value is calculated according to the first distance value and the second distance value. Among them, the spacing distance value is used to describe the spacing between the first distance value and the second distance value, that is, the spacing distance value is used to represent the similarity between the first plane and the second plane ρ. Afterwards, the product of the reciprocal of the inner product value and the spacing distance value can be calculated, and the first distance can be obtained according to the absolute value of the product. Optionally, it can be understood that the absolute value of the above product is used as the first distance. In this way, the first distance can be calculated by comprehensively considering the similarity between the normals of the planes and the similarity between the distance values ​​ρ.

[0104] It can be determined whether the inner product value is less than 0. If it is less than 0, the opposite number of the first distance value is subtracted from the second distance value, and the result is used as the spacing distance value. If it is not less than 0, the first distance value is subtracted from the second distance value, and the result is used as the spacing distance value.

[0105] Here is how to use Fig.10 The method shown is exemplified by selecting two target planes from more than two local planes.

[0106] Assume that the current initial weld is line_i, and the two planes of line_i are calculated as the first initial plane and the second initial plane. The normal of the first initial plane is n1 and the ρ parameter is ρ1, and the normal of the second initial plane is n2 and the parameter is ρ2. Initialize two values: min_dis_1 = 1e10, min_dis_2 = 1e10, min_dis_1 represents the closest distance from the detected local plane to the first initial plane, and min_dis_2 represents the closest distance from the detected local plane to the second initial plane.

[0107] Use variable i to traverse all local planes in the second detection result and obtain the normal n of local plane i i and the distance parameter ρ i Calculate n i n1, if the inner product is less than 0, let ρ i,1 =-ρ i , otherwise let ρ i,1 =ρ i, then calculate the distance from the local plane i to the first initial plane (i.e. the first distance mentioned above), and the distance calculation formula is: |(ρi,1-ρ1) / (ni·n1)|. The above distance formula comprehensively considers the similarity between the normals of the planes and the similarity between ρ. The closer the normals of the two planes are and the closer ρ is, the closer the distance between the two planes is. If the above distance is less than min_dis_1, let min_dis_1 be equal to the above distance, and record the label of the local plane at this time. The label is used to obtain the plane equation corresponding to the local plane in the subsequent calculation, which is convenient for calculating the second intersection line; conversely, if the above distance is greater than or equal to min_dis_1, min_dis_1 is not updated.

[0108] Similarly, calculate n i n2, if the inner product is less than 0, let ρ i,2 =-ρ i , otherwise let ρ i,2 =ρ i , then calculate the distance from local plane i to the second initial plane (i.e. the first distance mentioned above), the distance calculation formula is: |(ρi,2-ρ2) / (ni·n2)|. If the above distance is less than min_dis_2, set min_dis_2 equal to the above distance, and record the number of the local plane at this time, which is used to obtain the plane equation corresponding to the local plane in the future, so as to calculate the second intersection line; otherwise, if the above distance is greater than or equal to min_dis_2, min_dis_2 is not updated.

[0109] In this way, the local plane closest to the first initial plane and the local plane closest to the second initial plane can be determined from the local planes of the second detection result.

[0110] When the number of local planes in the second detection result is not greater than 2, that is, when the number of planes is 2, sub-step S333 may be executed.

[0111] Sub-step S332: directly use the two local planes in the second detection result as the first target plane and the second target plane.

[0112] When the number of detected local planes is two, the two detected local planes may be directly used as the first target plane and the second plane without performing the above-mentioned similarity calculation.

[0113] Sub-step S340, calculating and obtaining a second intersection line of the two target planes.

[0114] Sub-step S350, projecting the initial endpoint onto the second intersection line, and using the obtained third projection point as the target endpoint corresponding to the initial endpoint.

[0115] After determining the two target planes, the equation of the second intersection of the two target planes can be calculated according to the plane equations of the two target planes. The second intersection is a straight line of infinite length. When the second intersection is obtained, the initial endpoint corresponding to the local point cloud can be vertically projected onto the first intersection, and the obtained projection point is the third projection point, which can be used as the target endpoint corresponding to the corresponding initial endpoint.

[0116] In combination with the above description of determining two cylinders from an initial weld to determine a local point cloud or determining a cylinder to determine a local point cloud, it can be seen that, correspondingly, when two local point clouds are determined based on two initial endpoints, the two initial endpoints are projected onto the second intersection lines determined by the corresponding local point clouds to obtain target endpoints corresponding to the two initial endpoints, thereby obtaining a target weld. In this method, two second intersection lines need to be calculated and two projections need to be performed. In the case of determining a local point cloud based on two initial endpoints, both initial endpoints are projected onto the second intersection line determined based on the one local point cloud to obtain target endpoints corresponding to the two initial endpoints. In this method, only one second intersection line and one projection need to be calculated.

[0117] The following is an example of how to make local point adjustments.

[0118] Use i to traverse all initial welds and get the initial weld line_i. The starting point of line_i is line_i.p1_, the end point is line_i.p2_, the unit direction vector is line_i.t_, and the direction of the unit direction vector is from line_i.p1_ to line_i.p2_. Calculate the length of line_i and determine whether the length is greater than a preset length. If so, it indicates that the initial weld line_i has a longer length, and the starting point and end point of the initial weld line_i are adjusted locally. If not, it indicates that the initial weld line_i has a shorter length, and the starting point and end point are adjusted locally.

[0119] The following first introduces how to locally adjust the starting point and the end point of the initial weld line_i when the length of the initial weld line_i is greater than the preset length.

[0120] Set two reference points, p_in[0] = line_i.p1_, p_in[1] = line_i.p1_+100·line_i.t_, where p_in[0] is the starting point of the initial weld line_i; p_in[1] is the point that is 100 meters away from the starting point of the initial weld line_i to the end point of the initial weld line_i, that is, the target point mentioned above. According to the positions of the two points in p_in, a cylinder is formed in combination with the values ​​of seg_r and seg_l, and the cylinder is used to extract the local point cloud from the point cloud to be identified. The point cloud inside the cylinder is the extracted local point cloud, that is, the local point cloud corresponding to line_i.p1_. The extraction method is to use p_in[0] and p_in[1] to form the axis of the cylinder, seg_r as the radius of the cylinder, seg_l represents the distance extending outward along the axis of the cylinder, and the cylinder is as follows. Figure 8 shown.

[0121] Perform plane detection on the point cloud inside the cylinder (i.e., the local point cloud corresponding to the determined line_i.p1_). Then obtain the number of detected planes. If the number of detected planes is 2, no plane selection is required at this time, and these two planes are directly selected as two target planes. If the number of detected planes is greater than 2, perform plane selection as shown in sub-step S332 at this time to select two planes as two target planes.

[0122] After obtaining the two target planes, project p_in[0] onto the intersection of the two target planes to obtain the corresponding projection point p_out[0]. Assume that the adjusted line segment corresponding to line_i (i.e., the target weld) is line_i_ad, then the starting point of line_i_ad is line_i_ad.p1_=p_out[0]. The above process uses the local point cloud of the starting point of line_i to detect the plane in the local point cloud and adjusts the local point position of the starting point of line_i.

[0123] Next, the local point position of the end point of the initial weld line_i is adjusted in a similar manner.

[0124] Set two reference points, p_in[0] = line_i.p2_-100·line_i.t_, p_in[1] = line_i.p2_, p_in[1] is the end point of the initial weld line_i, and p_in[0] is the point 100 meters away from the end point of the initial weld line_i to the starting point of the initial weld line_i. According to the positions of the two points in p_in, a cylinder is formed by combining the values ​​of seg_r and seg_l, and the cylinder is used to intercept the local point cloud. The method of forming the cylinder is the same as before.

[0125] Perform plane detection on the point cloud inside the cylinder (i.e., the local point cloud corresponding to the determined line_i.p2_). Obtain the number of detected planes. If the number of detected planes is 2, directly select these two planes as two target planes. If the number of detected planes is greater than 2, perform the plane selection shown in sub-step S332 to select two target planes.

[0126] Project p_in[1] onto the intersection of the two target planes to obtain the corresponding projection point p_out[1]. The end point of line_i_ad is line_i_ad.p2_=p_out[1]. The above process uses the local point cloud of the end point of line_i to detect the plane in the local point cloud and adjust the local point position of the end point of line_i. In this way, the start and end positions of the initial weld line_i are adjusted.

[0127] Next, it is introduced how to adjust the local points of the starting point and the end point of the initial weld line_i at the same time when the length of the initial weld line_i is less than or equal to the preset length.

[0128] The process of adjusting the starting point and end point of the initial weld line_i at the same time is the same as the above process type, except that the starting point and end point of the initial weld line_i are adjusted locally at the same time. Set two reference points, p_in[0] = line_i.p1_, p_in[1] = line_i.p2_, and directly use the starting point and end point of the initial weld line_i as reference points. Use p_in, seg_r, and seg_l to obtain a local point cloud. Then perform plane detection on the local point cloud, and then determine two target planes from the detected planes. After that, project p_in (i.e., p_in[0], p_in[1]) onto the intersection of the two target planes to obtain p_out, then the starting point of the adjusted initial weld (i.e., the target weld) is line_i_ad.p1_ = p_out[0], and the end point of the adjusted initial weld (i.e., the target weld) is line_i_ad.p2_ = p_out[1].

[0129] By adjusting the starting point and end point of the initial weld by the above-mentioned local point adjustment method provided in this embodiment, a more accurate starting point and end point position can be obtained. Since a local point cloud near the starting point and end point is used, and a plane is detected in the local point cloud, the plane is closer to the actual object plane constituting the weld at this time, and the starting point and end point are projected onto the intersection line formed by the local plane to obtain an accurate projection point. In this embodiment, when performing local point adjustment, the problem of weld length is also considered. When the weld length is very long, the starting point and end point are adjusted locally respectively, so as to prevent the problem that the local plane at the starting point and the local plane at the end point are not completely consistent; when the weld length is short, the starting point and the end point are adjusted locally at the same time.

[0130] In order to execute the corresponding steps in the above embodiments and various possible methods, a method for implementing a linear weld recognition device 200 is provided below. Optionally, the linear weld recognition device 200 can adopt the above Figure 1 Further, please refer to Fig.11 , Fig.11 The block diagram of the linear weld recognition device 200 provided in the embodiment of the present application is shown in FIG. It should be noted that the basic principle and technical effect of the linear weld recognition device 200 provided in the present embodiment are the same as those of the above embodiment. For the sake of brief description, for the parts not mentioned in the present embodiment, reference can be made to the corresponding contents in the above embodiment. In the present embodiment, the linear weld recognition device 200 may include: a calculation module 210, a detection module 220 and a local point adjustment module 230.

[0131] The calculation module 210 is used to calculate the first intersection line according to the plane equations of the first initial plane and the second initial plane obtained by performing plane detection on the point cloud to be identified.

[0132] The detection module 220 is used to determine a line segment from the first intersection line as an initial weld according to the distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified;

[0133] The local point adjustment module 230 is used to adjust each initial endpoint of each initial weld according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified, so as to obtain the target endpoint corresponding to the initial endpoint. The two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a straight weld.

[0134] Optionally, the above modules can be stored in the form of software or firmware. Figure 1The memory 110 shown in the figure may be fixed in the operating system (OS) of the computer device 100 and may be Figure 1 Meanwhile, the data and program codes required for executing the above modules may be stored in the memory 110.

[0135] An embodiment of the present application also provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the linear weld recognition method is implemented.

[0136] In summary, the embodiment of the present application provides a linear weld recognition method, device, computer equipment and readable storage medium. First, the first intersection line is calculated according to the equations of two initial planes obtained by plane detection of the point cloud to be recognized; then, according to the distribution of points in the point cloud corresponding to each of the two initial planes in the point cloud to be recognized, a line segment is determined from the determined first intersection line as the initial weld; finally, for each initial weld, for each of the two initial endpoints of the initial weld, the initial endpoint is adjusted according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be recognized, and the obtained point is used as the target endpoint corresponding to the initial endpoint, wherein the two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a linear weld. In this way, by adjusting the local point positions of the two endpoints of the initial weld determined based on the plane intersection line, a more accurate linear weld position is obtained, which can avoid the situation that the initial weld is offset more than the actual linear weld when the initial weld is directly used as the linear weld to be recognized.

[0137] The above are merely embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A linear weld recognition method, characterized in that: The method comprises: Calculate a first intersection line according to the plane equations of the first initial plane and the second initial plane obtained by plane detection of the point cloud to be identified; According to the distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified, determining a line segment from the first intersection line as an initial weld; For each initial endpoint of each initial weld, the initial endpoint is adjusted according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified to obtain the target endpoint corresponding to the initial endpoint, wherein the two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a straight line weld.

2. The method according to claim 1, characterized in that For each initial endpoint of each initial weld, adjusting the initial endpoint according to a local plane in a local point cloud corresponding to the initial endpoint in the point cloud to be identified to obtain a target endpoint corresponding to the initial endpoint includes: For the initial endpoint, determining a local point cloud corresponding to the initial endpoint; Performing plane detection on the local point cloud to obtain a second detection result; Determine two local planes as target planes from the second detection result, wherein one of the two target planes is similar to the first initial plane, and the other is similar to the second initial plane; Calculate and obtain the second intersection line of the two target planes; The initial endpoint is projected onto the second intersection line, and the obtained third projection point is used as the target endpoint corresponding to the initial endpoint.

3. The method according to claim 2, characterized in that The step of determining two local planes as target planes from the second detection result includes: Determine whether the number of local planes in the second detection result is greater than 2; When the number of planes is greater than 2, the first similarity between each local plane and the first initial plane is calculated based on the plane information of each local plane in the second detection result and the plane information of the first initial plane, and the local plane corresponding to the largest first similarity is selected as the selected first target plane; and, the second similarity between each local plane and the second initial plane is calculated based on the plane information of each local plane and the plane information of the second initial plane, and the local plane corresponding to the largest second similarity is selected as the selected second target plane.

4. The method according to claim 3, characterized in that The plane information includes a normal vector and a distance value, wherein the distance value represents the distance between the plane and the origin of the coordinate system, and the distance value has a positive and negative sign; the similarity between two planes is represented by a first distance, and the greater the similarity, the smaller the first distance, and the first distance is calculated as follows: Calculate and obtain an inner product value of a first normal vector and a second normal vector, wherein the first normal vector is a normal vector of a first plane among the two planes, and the second normal vector is a normal vector of a second plane among the two planes; Obtaining an interval distance value according to a first distance value corresponding to the first plane and a second distance value corresponding to the second plane, wherein the interval distance value is used to describe the interval between the first distance value and the second distance value; The product of the reciprocal of the inner product value and the interval distance value is calculated, and the first distance is obtained according to the absolute value of the product.

5. The method according to claim 3, characterized in that: The method of determining two local planes as target planes from the second detection result further includes: When the number of the planes is 2, the two local planes in the second detection result are directly used as the first target plane and the second target plane.

6. The method according to claim 2, characterized in that The step of determining a local point cloud corresponding to the initial endpoint includes: Determine a cylinder according to the initial endpoint and the initial weld where the initial endpoint is located, wherein the initial endpoint is located on the axis of the cylinder, and the axis of the cylinder is located on the corresponding first intersection line; The determined cylinder is used to determine a local point cloud corresponding to the initial endpoint from the point cloud to be identified.

7. The method according to claim 6, characterized in that Determining a cylinder according to the initial endpoint and the initial weld where the initial endpoint is located includes: In the case where the weld length of the initial weld is greater than a preset length, a point is determined on the initial weld as a target point for the initial endpoint, and a corresponding cylinder is determined according to the preset radius, the initial endpoint and the target point, wherein the target point is located between the initial endpoint and another initial endpoint of the initial weld, and the local point clouds corresponding to the two initial endpoints of the initial weld are different; When the weld length is less than or equal to the preset length, a corresponding cylinder is determined according to the preset radius and the two initial endpoints of the initial weld, wherein the two initial endpoints of the initial weld correspond to the same local point cloud, and the two target endpoints corresponding to the initial weld are obtained by projecting the two initial endpoints of the initial weld onto the same second intersection line.

8. The method according to any one of claims 1 to 7, characterized in that: The method of determining a line segment from the first intersection line as an initial weld according to the distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified includes: For the first point cloud, all points in the first point cloud that are located near the first intersection line are projected onto the first intersection line, and when the number of clusters is not determined, the obtained first projection points are clustered to obtain at least one first projection point set; For the second point cloud, all points in the second point cloud that are located near the first intersection line are projected onto the first intersection line, and when the number of clusters is not determined, the obtained second projection points are clustered to obtain at least one second projection point set; It is analyzed whether there is an intersection between the first line segment intervals corresponding to the first projection point sets and the second line segment intervals corresponding to the second projection point sets. If there is an intersection, the initial weld is determined according to the existing intersection.

9. The method according to claim 8, characterized in that Determining the initial weld according to the existing intersection includes: Determine the closest points corresponding to the two intersection endpoints of the intersection from the first point cloud and the second point cloud, and calculate the second distance between each intersection endpoint and the corresponding closest point; When the calculated second distances are all less than or equal to the first preset distance, the line segment indicated by the intersection is used as an initial weld; When at least one second distance is greater than the first preset distance, the line segment indicated by the intersection is not used as an initial weld.

10. A linear weld identification device, characterized in that: The device comprises: A calculation module, used for calculating a first intersection line according to plane equations of a first initial plane and a second initial plane obtained by plane detection on the point cloud to be identified; a detection module, configured to determine a line segment from the first intersection line as an initial weld according to distribution of points in a first point cloud corresponding to the first initial plane and a second point cloud corresponding to the second initial plane in the point cloud to be identified; The local point adjustment module is used to adjust each initial endpoint of each initial weld according to the local plane in the local point cloud corresponding to the initial endpoint in the point cloud to be identified, so as to obtain the target endpoint corresponding to the initial endpoint, wherein the two target endpoints corresponding to an initial weld are the two endpoints of a target weld, and the target weld is a straight weld.

Images