Flat plate lap joint workpiece model-free construction method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a flat plate lapping workpiece model-free construction method and device, electronic equipment and storage medium, relating to the field of workpiece construction, the method comprising: determining the current point cloud of the flat plate lapping workpiece, determining the first point cloud before the current point cloud, performing local registration splicing based on the first point cloud and the current point cloud, obtaining a rotation matrix and a translation vector, in the case that the first point cloud corresponds to a structure list containing a flat plate lapping structure, performing inverse transformation on the flat plate lapping structure in the structure list based on the rotation matrix and the translation vector, obtaining the inverse transformed flat plate lapping structure, and detecting the plane in the current point cloud based on the inverse transformed flat plate lapping structure, so as to improve the detection efficiency.

Description

Technical Field

[0001] This invention relates to the field of workpiece construction, and more specifically, to a method, apparatus, electronic device, and storage medium for model-free construction of workpieces by overlapping flat plates. Background Technology

[0002] Currently, when there is no model to construct for plate lap joint workpieces, plane detection and structure finding are performed directly on each input point cloud. When acquiring point clouds of plate lap joint workpieces using structured light or line scan mode from a 3D camera, the point clouds have the following characteristics: spurious data points are prone to appear in the plate lap weld. The two planes constituting the plate lap weld satisfy the same plane equation and are very close to each other. Because of the presence of spurious data points in the weld, the downsampled point cloud and ordinary plane detection algorithms cannot detect the two planes constituting the plate lap weld.

[0003] To accurately detect the two planes constituting the lap weld of a flat plate during the planar inspection stage, existing techniques typically employ the following method to separate the two planes. First, instead of downsampling the point cloud, the direct output point cloud is used for inspection. Edge detection is performed on the input point cloud, and then "double edge points" are identified for the detected edges. "Double edge points" are edge points that appear in pairs and will appear near the lap weld of the flat plate. Points inside the double edge points are deleted, i.e., spurious data points inside the lap weld of the flat plate are removed. Normal planar inspection is then performed, thus correctly detecting the two planes constituting the lap weld of the flat plate.

[0004] Since the two planes constituting the lap weld of the flat plate satisfy the same plane equation and are very close to each other, in order to correctly separate the two planes during the plane detection stage, it is necessary to use direct output point cloud. The number of points in the direct output point cloud is approximately in the millions. Using direct output point cloud for plane detection is time-consuming. When building the workpiece without a model, it is necessary to take pictures of the entire workpiece, that is, to take about 10 point cloud pictures. Each point cloud is inspected using direct output point cloud. The entire model-free construction time is long. Summary of the Invention

[0005] The purpose of this invention is to provide a model-free construction method, apparatus, electronic device, and storage medium for flat plate overlapping workpieces, which can improve the detection efficiency of flat plate overlapping workpieces.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a model-free construction method for overlapping flat workpieces, the method comprising: Determine the current point cloud of the flat plate overlapping workpiece; Determine the first point cloud prior to the current point cloud; Based on the first point cloud and the current point cloud, local registration and stitching are performed to obtain the rotation matrix and translation vector; If the structure list corresponding to the first point cloud contains a plate overlapping structure, the plate overlapping structure in the structure list is inversely transformed based on the rotation matrix and the translation vector to obtain the inversely transformed plate overlapping structure. The planes in the current point cloud are detected based on the plate overlapping structure after inverse transformation.

[0007] In an optional implementation, the method further includes: If the structure list of the first point cloud does not contain a flat plate overlapping structure, then the flat plate overlapping structure in the current point cloud is detected.

[0008] In an optional implementation, the step of detecting planes in the current point cloud based on the inverse-transformed plate overlapping structure includes: Let variable i = 0; If the variable i is less than the number of plate overlap structures in the structure list, the i-th plate overlap structure is obtained from the structure list; Determine whether the i-th flat plate overlapping structure meets the preset conditions; If the i-th plate lap structure meets the preset conditions, the weld of the i-th plate lap structure is stored in the weld table; Let variable j = 0; When the variable j is less than the number of welds in the weld table, the j-th weld is obtained from the weld table; The current point cloud is cropped based on the j-th weld to obtain a second point cloud; The plane is detected based on the current point cloud and the second point cloud.

[0009] In an optional implementation, the step of determining whether the i-th flat plate overlap structure meets the preset conditions includes: Determine the weld length of the i-th plate lap joint structure; Determine whether the weld length is greater than or equal to a preset length; If the weld length is greater than or equal to the preset length, determine the number of votes for the i-th plate overlap structure; Determine whether the number of votes is greater than or equal to the preset number of votes; If the number of votes is greater than or equal to the preset number of votes, the i-th flat plate overlapping structure is determined to meet the preset conditions.

[0010] In an optional implementation, the step of cropping the current point cloud based on the j-th weld to obtain a second point cloud includes: Using the j-th weld as the axis of a cylinder, the current point cloud is truncated with a preset radius; The extracted point cloud is used as the second point cloud.

[0011] In an optional implementation, the step of detecting the plane based on the current point cloud and the second point cloud includes: Based on the second point cloud, the point clouds in the current point cloud are removed to obtain the third point cloud after removal; The plane is detected based on the third point cloud and the second point cloud.

[0012] In an optional implementation, the step of detecting the plane based on the third point cloud and the second point cloud includes: Remove the false data points from the second point cloud to obtain the fourth point cloud; The fourth point cloud and the third point cloud are merged to obtain a merged point cloud; The merged point cloud is downsampled, and planar detection is performed based on the downsampled merged point cloud.

[0013] Secondly, embodiments of this application provide a modelless construction device for flat plate overlapping workpieces, the device performing a modelless construction method for flat plate overlapping workpieces.

[0014] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the model-free construction method for flat plate overlapping workpieces.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the model-free construction method for the flat plate overlapping workpiece.

[0016] This application has the following beneficial effects: This application determines the current point cloud of the plate-overlapping workpiece, determines the first point cloud preceding the current point cloud, performs local registration and stitching based on the first point cloud and the current point cloud to obtain a rotation matrix and a translation vector, and if the plate-overlapping structure is included in the structure list corresponding to the first point cloud, performs an inverse transformation on the plate-overlapping structure in the structure list based on the rotation matrix and the translation vector to obtain the inversely transformed plate-overlapping structure, and detects the planes in the current point cloud based on the inversely transformed plate-overlapping structure to improve detection efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A block diagram of an electronic device provided in an embodiment of the present invention; Figure 2 This is one of the flowcharts illustrating a method for constructing a modelless workpiece by overlapping flat plates according to an embodiment of the present invention; Figure 3 This is a second schematic flowchart of a method for constructing a flat plate overlapping workpiece without a model, provided by an embodiment of the present invention. Figure 4 This is the third flowchart illustrating a method for constructing a modelless workpiece by overlapping flat plates, as provided in an embodiment of the present invention. Figure 5 This is the fourth flowchart illustrating a method for constructing a modelless workpiece by overlapping flat plates, as provided in an embodiment of the present invention. Figure 6 This is the fifth flowchart illustrating a method for constructing a modelless workpiece by overlapping flat plates, as provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0021] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0022] In the description of this invention, it should be noted that if terms such as "upper," "lower," "inner," or "outer" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of this invention is usually placed, they are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0023] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0024] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0025] Extensive research by the inventors revealed that existing technologies typically separate the two planes using the following method: First, instead of downsampling the point cloud, direct point cloud detection is used. Edge detection is performed on the input point cloud, and then "double edge points" are identified for the detected edges. "Double edge points" are edge points that appear in pairs, and they appear near the lap weld of the flat plate. Points inside the double edge points are deleted, i.e., spurious data points inside the lap weld of the flat plate are removed. Then, normal plane detection is performed, thus correctly detecting the two planes that constitute the lap weld of the flat plate. However, the existing detection method is time-consuming.

[0026] In view of the above-mentioned problems, this embodiment provides a model-free construction method, apparatus, electronic device, and storage medium for flat plate overlapping workpieces. It can determine the current point cloud of the flat plate overlapping workpiece, determine the first point cloud preceding the current point cloud, perform local registration and stitching based on the first point cloud and the current point cloud to obtain a rotation matrix and translation vector, and if the structure list corresponding to the first point cloud contains a flat plate overlapping structure, perform an inverse transformation on the flat plate overlapping structure in the structure list based on the rotation matrix and translation vector to obtain the inversely transformed flat plate overlapping structure. Based on the inversely transformed flat plate overlapping structure, planes in the current point cloud are detected to improve detection efficiency. The solution provided in this embodiment is described in detail below.

[0027] This embodiment provides an electronic device capable of constructing flat, overlapping workpieces without a model. In one possible implementation, the electronic device can be a user terminal, such as, but not limited to, servers, smartphones, personal computers (PCs), tablet computers, personal digital assistants (PDAs), mobile internet devices (MIDs), and image acquisition devices.

[0028] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the structure of the electronic device 100 provided in the embodiments of this application. The electronic device 100 may further include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0029] The electronic device 100 includes a flat plate overlapping workpiece modelless construction device 110, a memory 120, and a processor 130.

[0030] The components of the memory 120 and processor 130 are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The flat-plate overlapping workpiece model-free construction device 110 includes at least one software function module that can be stored in the memory 120 in the form of software or firmware or embedded in the operating system (OS) of the electronic device 100. The processor 130 is used to execute the executable modules stored in the memory 120, such as the software function modules and computer programs included in the flat-plate overlapping workpiece model-free construction device 110.

[0031] The memory 120 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 120 is used to store programs, and the processor 130 executes the programs after receiving execution instructions.

[0032] Please refer to Figure 2 , Figure 2 For application Figure 1 The flowchart below shows a method for model-free construction of a flat plate overlapping workpiece for an electronic device 100. The method includes a detailed description of each step.

[0033] S201: Determine the current point cloud of the flat plate overlapping workpiece.

[0034] The robot or scanning device is moved to the nth shooting position, triggering the LiDAR or structured light sensor to acquire a frame of point cloud, which is recorded as the current point cloud. n is compared with the total number of point cloud images. If n is less than the total number of point cloud images, step S202 is executed; otherwise, the algorithm terminates. The total number of point cloud images represents the total number of point cloud images required for model construction.

[0035] S202: Determine the first point cloud before the current point cloud.

[0036] Read the stitched point cloud and denote it as the first point cloud. For example, when n is 3, the first point cloud is the point cloud stitched together from the point cloud taken at n=1 and the point cloud taken at n=2.

[0037] The first point cloud belongs to the existing stitched point cloud and has stable global coordinates. If n=1, the first point cloud does not exist. The current point cloud with n=1 constitutes the existing first point cloud. After each new point cloud is captured, the new point cloud is locally registered and stitched with the existing stitched point cloud, and the newly captured part is added to the existing stitched point cloud.

[0038] S203: Perform local registration and stitching based on the first point cloud and the current point cloud to obtain the rotation matrix and translation vector.

[0039] Geometric features, such as FPFH, edge points, and planar patches, can be extracted between the current point cloud and the first point cloud. Local registration algorithms such as ICP or NDT can be used to solve for the optimal rigid body transformation, thereby obtaining the rotation matrix and the corresponding translation vector from the current point cloud to the first point cloud.

[0040] S204: If the structure list corresponding to the first point cloud contains a plate overlapping structure, perform an inverse transformation on the plate overlapping structure in the structure list based on the rotation matrix and translation vector to obtain the inverse transformed plate overlapping structure.

[0041] The structure list corresponding to the first point cloud stores the geometric structures detected in the historical point clouds, such as flat plate overlapping structures, and includes the number of votes.

[0042] Query the structure list corresponding to the first point cloud. If there is a plate lap structure in the first point cloud, the plate lap structure is composed of two planes that make up the plate lap weld. Perform an inverse transformation on the plate lap structure in the structure list based on the rotation matrix and translation vector to obtain the inverse transformed plate lap structure. The purpose of the inverse transformation is to align the existing structure with the current point cloud.

[0043] If the structure list of the first point cloud does not contain the planar overlapping structure, the planar overlapping structure in the current point cloud is detected. The specific detection method can be as follows: perform lightweight preprocessing on the current point cloud, including removing invalid points, performing voxel downsampling, and performing statistical filtering to remove obvious outliers, etc., and use RANSAC or region growing algorithm to iteratively extract the planar structure in the point cloud. Perform geometric relationship analysis on the detected multiple planes to detect the planar overlapping structure from the first point cloud.

[0044] S205: Detect the flat plate overlapping structure in the current point cloud based on the flat plate overlapping structure after inverse transformation.

[0045] When a plate overlap structure has been detected in the first point cloud, the structure is stored in the structure list. Then, when performing planar detection on the new point cloud, the plate overlap structure in the structure list is read in and the point cloud is extracted using the direction vector of the plate overlap weld. The extracted point cloud is subjected to double edge detection and spurious data point removal. The remaining point cloud is downsampled normally. Then, the two parts of the point cloud are combined and planar detection is performed, thereby reducing the overall running time.

[0046] There are several ways to detect flat plate overlap structures in the current point cloud based on the flat plate overlap structure after inverse transformation. In one implementation method, such as Figure 3 As shown, it includes the following steps: S301: Let variable i = 0.

[0047] S302: If variable i is less than the number of plate overlapping structures in the structure list, obtain the i-th plate overlapping structure from the structure list.

[0048] S303: Determine whether the i-th plate overlap structure meets the preset conditions.

[0049] S304: If the i-th plate lap structure meets the preset conditions, the weld of the i-th plate lap structure is stored in the weld table.

[0050] Let the structure traversal index i = 0, which is used to sequentially access the inverse-transformed flat plate overlapping structure in the structure list of the first point cloud.

[0051] Determine if i is less than the number of plate overlapping structures in the structure list. If not, end the traversal. If yes, extract the i-th plate overlapping structure from the structure list. This structure has been mapped to the current point cloud coordinate system by the aforementioned inverse transformation.

[0052] The i-th plate overlap structure is verified to determine whether the i-th plate overlap structure meets the preset conditions, including, but not limited to, the weld length of the i-th plate overlap structure being not less than the preset length threshold, and the cumulative number of votes for the i-th plate overlap structure in the historical shooting point cloud being not less than the preset number of votes.

[0053] For the i-th plate lap structure that passes the preset condition verification, extract the start and end points of the plate lap weld of the i-th plate lap structure, store the weld formed by the two points in the weld table as the geometric constraint for subsequent point cloud truncation, then let i = i+1, return to step S302, until all plate lap structures have been traversed.

[0054] S305: Set variable j = 0.

[0055] S306: When the variable j is less than the number of welds in the weld table, retrieve the j-th weld from the weld table.

[0056] S307: Extract the current point cloud based on the j-th weld to obtain the second point cloud.

[0057] S308: Detect the plane based on the current point cloud and the second point cloud.

[0058] Let the weld traversal index j=0, which is used to sequentially access each weld in the weld table. Determine whether j is less than the total number of welds in the weld table. If not, end the traversal. If so, extract the j-th weld from the weld table as the current cutting axis. Use the j-th weld to cut the current point cloud and obtain the cut point cloud, which is the second point cloud.

[0059] The plane is detected based on the current point cloud and the captured second point cloud. That is, the plate lap weld detected in the previous point cloud is used as prior information to assist the plane detection of the subsequent point cloud. The planar lap structure is detected based on the plane detection results, thereby reducing the detection time and improving the detection efficiency.

[0060] There are multiple ways to determine whether the i-th plate overlap structure meets the preset conditions. In one implementation, such as... Figure 4 As shown, it includes the following steps: S401: Determine the weld length of the i-th plate lap joint structure.

[0061] S402: Determine whether the weld length is greater than or equal to the preset length.

[0062] S403: When the weld length is greater than or equal to the preset length, determine the number of votes for the i-th plate lap structure.

[0063] S404: Determine whether the number of votes is greater than or equal to the preset number of votes.

[0064] S405: If the number of votes is greater than or equal to the preset number of votes, determine that the i-th flat plate overlapping structure meets the preset conditions.

[0065] Extract the starting and ending coordinates of the i-th plate lap structure from the structure list, calculate the Euclidean distance between the two points, and use it as the weld length of the i-th plate lap structure. Compare the calculated weld length with the preset length. If the weld length of the i-th plate lap structure is less than the preset length, it is determined that the i-th plate lap structure does not meet the preset condition, and the subsequent processing of the i-th plate lap structure is terminated.

[0066] When the weld length of the i-th plate lap structure is greater than or equal to the preset length, the subsequent preset condition determination is executed.

[0067] When the weld length of the i-th plate overlap structure is greater than or equal to the preset length, the voting attribute of the i-th plate overlap structure is further read, that is, the voting counter associated with the i-th plate overlap structure is extracted from the structure list. The number of votes of the voting counter associated with the i-th plate overlap structure represents the number of times the i-th plate overlap structure has been successfully detected and matched in the historical consecutive frames of point cloud. Each time a structure that is geometrically consistent with the i-th plate overlap structure is detected in the current point cloud, the number of votes is automatically incremented.

[0068] The number of votes for the i-th flat plate overlap structure is compared with the preset number of votes. If the number of votes for the i-th flat plate overlap structure is less than the preset number of votes, the subsequent processing of the i-th flat plate overlap structure is terminated. If the number of votes for the i-th flat plate overlap structure is greater than or equal to the preset number of votes, the i-th flat plate overlap structure is determined to meet the preset condition, and the i-th flat plate overlap structure is used as prior information to perform planar detection on the current point cloud.

[0069] There are several ways to extract a second point cloud from the current point cloud based on the j-th weld seam. In one such method, such as... Figure 5 As shown, it includes the following steps: S501: Using the j-th weld as the axis of the cylinder, extract the current point cloud with a preset radius.

[0070] S502: Use the extracted point cloud as the second point cloud.

[0071] There are several ways to implement the interception by taking the j-th weld as the axis and the preset radius as the cylinder radius. In one implementation, an infinitely long cylinder can be constructed with the j-th weld as the axis and the preset radius as the cylinder radius. The Euclidean distance from each point in the current point cloud to the axis is calculated, and points with a distance less than or equal to the preset radius are extracted to form a second point cloud.

[0072] There are multiple ways to detect a plane based on the current point cloud and the second point cloud. In one implementation method, such as... Figure 6 As shown, it includes the following steps: S601: Based on the second point cloud, remove the point cloud from the current point cloud to obtain the third point cloud after removal.

[0073] S602: Remove the false data points in the second point cloud to obtain the fourth point cloud.

[0074] S603: Merge the fourth point cloud and the third point cloud to obtain the merged point cloud.

[0075] S604: Downsample the merged point cloud and perform plane detection based on the downsampled merged point cloud.

[0076] The second point cloud, which is truncated from the current point cloud with the j-th weld as the axis of the cylinder and with a preset radius, is removed from the current point cloud. That is, the points corresponding to the second point cloud are removed from the current point cloud to form the third point cloud. This step uses the welds in the previously detected plate lap structure to truncate the current input point cloud. The truncated part is the removal of dummy data points from the second point cloud. The outer part is directly downsampled. In this way, the current input point cloud is processed by region by using prior information.

[0077] The flat plate lap weld of the current point cloud must be located in the second point cloud. Perform double edge detection and remove false data points on the second point cloud. Let the false data point be cloud_nonvalid. The point cloud from which the false data point is removed is the fourth point cloud. Merge the fourth point cloud and the third point cloud. Downsample the merged point cloud. Perform plane detection on the downsampled point cloud. Reassign cloud_nonvalid to the plane. The algorithm ends.

[0078] The model-free construction method for plate-overlapping workpieces provided in this application utilizes prior information about the detected plate-overlapping structure to extract the current point cloud. Complex calculations such as edge detection and spurious data removal are performed only on the extracted point cloud. For the outer point cloud, downsampling and planar detection are directly applied, achieving the effect of region-based point cloud detection. Since the extracted point cloud represents only a small portion of the input point cloud, and normal downsampling and planar detection are still performed on the point cloud outside the extracted portion, significant computation time can be saved compared to performing edge detection and spurious data removal on the entire output point cloud. For the model-free construction of the entire plate-overlapping workpiece, since dozens of point cloud images need to be captured, and each image saves considerable computation time, the overall construction process is significantly more efficient than before.

[0079] This application embodiment also provides a modelless construction device 110 for flat plate overlapping workpieces, which implements the modelless construction method for flat plate overlapping workpieces.

[0080] This application also provides an electronic device 100, which includes a processor 130 and a memory 120. The memory 120 stores computer-executable instructions, which, when executed by the processor 130, implement the model-free construction method for the flat plate overlapping workpiece.

[0081] This application embodiment also provides a computer-readable storage medium storing a computer program. When the computer program is executed by the processor 130, it implements the model-free construction method for the plate-joint workpiece.

[0082] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0083] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. If the function is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0084] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0085] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A model-free construction method for overlapping flat workpieces, characterized in that, The method includes: Determine the current point cloud of the flat plate overlapping workpiece; Determine the first point cloud prior to the current point cloud; Based on the first point cloud and the current point cloud, local registration and stitching are performed to obtain the rotation matrix and translation vector; If the structure list corresponding to the first point cloud contains a plate overlapping structure, the plate overlapping structure in the structure list is inversely transformed based on the rotation matrix and the translation vector to obtain the inversely transformed plate overlapping structure. The planes in the current point cloud are detected based on the plate overlapping structure after inverse transformation.

2. The method according to claim 1, characterized in that, The method further includes: If the structure list of the first point cloud does not contain a flat plate overlapping structure, then the flat plate overlapping structure in the current point cloud is detected.

3. The method according to claim 1, characterized in that, The step of detecting planes in the current point cloud based on the plate overlapping structure after inverse transformation includes: Let variable i = 0; If the variable i is less than the number of plate overlap structures in the structure list, the i-th plate overlap structure is obtained from the structure list; Determine whether the i-th flat plate overlapping structure meets the preset conditions; If the i-th plate lap structure meets the preset conditions, the weld of the i-th plate lap structure is stored in the weld table; Let variable j = 0; When the variable j is less than the number of welds in the weld table, the j-th weld is obtained from the weld table; The current point cloud is cropped based on the j-th weld to obtain a second point cloud; The plane is detected based on the current point cloud and the second point cloud.

4. The method according to claim 3, characterized in that, The step of determining whether the i-th plate overlap structure meets the preset conditions includes: Determine the weld length of the i-th plate lap joint structure; Determine whether the weld length is greater than or equal to a preset length; If the weld length is greater than or equal to the preset length, determine the number of votes for the i-th plate lap structure; Determine whether the number of votes is greater than or equal to the preset number of votes; If the number of votes is greater than or equal to the preset number of votes, the i-th flat plate overlapping structure is determined to meet the preset conditions.

5. The method according to claim 3, characterized in that, The step of cropping the current point cloud based on the j-th weld to obtain a second point cloud includes: Using the j-th weld as the axis of a cylinder, the current point cloud is truncated with a preset radius; The extracted point cloud is used as the second point cloud.

6. The method according to claim 3, characterized in that, The step of detecting the plane based on the current point cloud and the second point cloud includes: Based on the second point cloud, the point clouds in the current point cloud are removed to obtain the third point cloud after removal; The plane is detected based on the third point cloud and the second point cloud.

7. The method according to claim 6, characterized in that, The step of detecting the plane based on the third point cloud and the second point cloud includes: Remove the false data points from the second point cloud to obtain the fourth point cloud; The fourth point cloud and the third point cloud are merged to obtain a merged point cloud; The merged point cloud is downsampled, and planar detection is performed based on the downsampled merged point cloud.

8. A model-free construction device for overlapping flat workpieces, characterized in that, The apparatus performs the method as described in any one of claims 1-7.

9. An electronic device, characterized in that, The method includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

10. A readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1-7.

Images