A splicing gap detection method and device, electronic equipment and storage medium
By acquiring point cloud data and performing segmentation and plane fitting, the width of splicing gaps is automatically detected, solving the problems of low detection accuracy and low efficiency in existing technologies, and achieving efficient and accurate splicing gap detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI AIRCRAFT MFG
- Filing Date
- 2026-03-13
- Publication Date
- 2026-06-16
Smart Images
Figure CN122222952A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of detection technology, and in particular to a method, apparatus, electronic device, and storage medium for detecting seam gaps. Background Technology
[0002] In the aerospace and automotive industries, automated tape layers are used to lay prepregs for composite materials. During the composite material laying process, gaps exist between the prepreg tapes. To ensure the quality of the composite material laying, the width of these gaps needs to be inspected to ensure it meets process requirements.
[0003] In existing technologies, inspectors visually assess whether the width of the splice seams meets requirements. However, this manual inspection requires stopping the automatic tape-laying machine, which impacts its laying efficiency and consequently, component production efficiency. Furthermore, relying on visual inspection by personnel depends on their experience, resulting in low accuracy and efficiency in determining the splice seam width. Summary of the Invention
[0004] This invention provides a method, apparatus, electronic device, and storage medium for detecting seam width, thereby achieving automatic detection of seam width and improving detection efficiency and accuracy.
[0005] According to one aspect of the present invention, a method for detecting splice gaps is provided, comprising: Acquire point cloud data of the target area, including stitching seams within the target area; Determine region segmentation information based on the directional information corresponding to the point cloud data of the target region; The point cloud data of the target region is segmented based on the region segmentation information to obtain point cloud data of multiple first surface sub-regions; Plane fitting is performed on the point cloud data of each first surface sub-region to obtain the fitting plane corresponding to each first surface sub-region; the point cloud data of the first surface sub-region is filtered based on the fitting plane to determine the target point cloud data. The width information of the splicing gap is determined based on the target point cloud data.
[0006] According to another aspect of the present invention, a splice gap detection device is provided, comprising: The point cloud data acquisition module is used to acquire point cloud data of a target area, including the stitching seams. The region segmentation information determination module is used to determine region segmentation information based on the directional information corresponding to the point cloud data of the target region. The point cloud data segmentation module is used to segment the point cloud data of the target area based on the region segmentation information to obtain point cloud data of multiple first surface sub-regions; The target point cloud data determination module is used to perform plane fitting on the point cloud data of each first surface sub-region to obtain the fitting plane corresponding to the first surface sub-region; and to filter the point cloud data of the first surface sub-region based on the fitting plane to determine the target point cloud data. The width information determination module is used to determine the width information of the splicing gap based on the target point cloud data.
[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the splice gap detection method of any embodiment of the present invention.
[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the splicing gap detection method of any embodiment of the present invention.
[0009] The technical solution of this invention acquires point cloud data of a target region, including stitching seams, providing comprehensive data support for subsequent analysis and processing, ensuring efficient and accurate execution of subsequent tasks. Based on the directional information corresponding to the point cloud data of the target region, it determines region segmentation information, providing accurate data support for the segmentation of the point cloud data of the target region. Based on the region segmentation information, it segments the point cloud data of the target region to obtain point cloud data of multiple first curved surface sub-regions, realizing the segmentation of the target region and its point cloud data, providing a refined data foundation for subsequent analysis and processing. Finally, it performs planar fitting on the point cloud data of each first curved surface sub-region to obtain the corresponding fitted area for each first curved surface sub-region. The fitting plane is used to filter the point cloud data of the first curved surface sub-region to determine the target point cloud data. This filtering of point cloud data for the first curved surface sub-region can identify the point cloud data corresponding to the splicing seam, providing accurate data support for subsequent analysis and processing and reducing the computational load of subsequent tasks. Based on the target point cloud data, the width information of the splicing seam is determined, realizing the detection of the splicing seam width information. This solves the problems of low accuracy and low detection efficiency of the existing technology that relies on visual observation by inspectors to detect the width of the splicing seam. It can detect the width information of the splicing seam without stopping the automatic tape laying machine, improving the detection efficiency and the accuracy of the splicing seam width information.
[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0012] Figure 1 This is a flowchart of a splicing gap detection method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of point cloud data of a target area provided by the present invention; Figure 3 This is a flowchart of another splicing gap detection method provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a third projection data provided in an embodiment of the present invention; Figure 5This is a schematic diagram of the structure of a splicing gap detection device provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0015] Figure 1 This is a flowchart of a splicing gap detection method provided in an embodiment of the present invention. This embodiment is applicable to situations requiring real-time detection of splicing gaps in materials. The method can be executed by a splicing gap detection device, which can be implemented in hardware and / or software. This device can be configured in the electronic device provided in this embodiment of the invention, such as a server, computer, or mobile terminal, for example, a mobile terminal such as a mobile phone or tablet computer. Figure 1 As shown, the method specifically includes the following steps: S110. Obtain point cloud data of the target area, including the stitching seams within the target area.
[0016] During material installation, seams exist between materials. These materials include, but are not limited to, composite materials. This invention is used to detect the width of these seams to ensure that the installed components meet process requirements. The target area is the region where seam detection is required. The target area includes the seams and may also include the materials themselves. The point cloud data of the target area can be obtained by scanning the target area with a scanning device. Optionally, the scanning device includes, but is not limited to, a 3D camera. The point cloud data of the target area includes the 3D coordinate information of the target area. Optionally, the point cloud data of the target area includes the 3D coordinate information of the seams within the target area. The point cloud data of the target area can also be obtained from a point cloud database. For example, it can be matched in a point cloud database based on the unique identifier of the target area, and the matched point cloud data can be used as the point cloud data of the target area. See also [example description]. Figure 2 , Figure 2 This is a schematic diagram of point cloud data of a target area provided by the present invention.
[0017] Specifically, the target area is scanned by a scanning device to obtain point cloud data of the target area, providing comprehensive data support for subsequent analysis and processing, and ensuring that subsequent tasks can be executed efficiently and accurately.
[0018] S120. Determine the region segmentation information based on the direction information corresponding to the point cloud data of the target region.
[0019] The directional information represents the geometric distribution trend of the point cloud data of the target region in space. Optionally, the directional information corresponding to the point cloud data of the target region includes the length and width directions of the point cloud data of the target region. Optionally, the directional information corresponding to the point cloud data of the target region includes the height direction of the point cloud data of the target region.
[0020] Optionally, the process for determining the orientation information corresponding to the point cloud data of the target region is as follows: A covariance matrix is constructed based on the point cloud data of the target region; the covariance matrix is solved to determine its eigenvectors; and the orientation information corresponding to the point cloud data of the target region is determined based on the eigenvectors of the covariance matrix. The covariance matrix can be constructed based on the point cloud data of the target region. For example, the average coordinates of the three-dimensional coordinates in the point cloud data of the target region can be calculated. The point cloud data of the target region can be decentralized based on the average coordinates of the three-dimensional coordinates to obtain centralized point cloud data. This centralized point cloud data is then input into a covariance matrix construction model for processing to obtain the covariance matrix. The covariance matrix construction model includes, but is not limited to, neural network models and mathematical models. The covariance matrix is solved to obtain its eigenvectors, and these eigenvectors are used as the orientation information corresponding to the point cloud data of the target region.
[0021] Region segmentation information is used to divide point cloud data of a target region. Optionally, region segmentation information may include equal division information of the point cloud data of the target region. For example, the region segmentation information can be m×n, where m represents the number of equal divisions along the length direction of the point cloud data of the target region, and n represents the number of equal divisions along the width direction of the point cloud data of the target region. Region segmentation information can be determined based on the directional information of the point cloud data of the target region. For example, the directional information of the point cloud data of the target region can be input into a region segmentation information determination model for processing to obtain region segmentation information. The region segmentation information determination model includes, but is not limited to, neural network models and mathematical models.
[0022] Specifically, the directional information corresponding to the point cloud data of the target area is input into the region segmentation information determination model for processing to obtain region segmentation information, which provides accurate data support for the segmentation of the point cloud data of the target area.
[0023] S130. Based on the region segmentation information, the point cloud data of the target region is segmented to obtain point cloud data of multiple first surface sub-regions.
[0024] The target region has curvature, with different locations within the target region corresponding to different curvatures. Segmenting the point cloud data of the target region based on region segmentation information can be achieved by dividing the target region into multiple equal regions. Each equal region includes the corresponding point cloud data, and these segmented regions are called the first curved surface sub-regions. The first curved surface sub-regions are the regions obtained by segmenting the target region. Different first curved surface sub-regions have different curvatures.
[0025] Specifically, the target region is segmented based on the region segmentation information to obtain multiple segmented regions, which are called first surface sub-regions. Each first surface sub-region includes the point cloud data within its range, thus realizing the segmentation of the target region and its point cloud data, providing a refined data foundation for subsequent analysis and processing.
[0026] S140. Perform plane fitting on the point cloud data of each first surface sub-region to obtain the fitting plane corresponding to each first surface sub-region; filter the point cloud data of the first surface sub-region based on the fitting plane to determine the target point cloud data.
[0027] The fitting plane is a two-dimensional plane representing the spatial distribution of point cloud data in the first curved surface sub-region. The fitting plane can be represented by a plane expression, such as a plane equation. Each first curved surface sub-region corresponds to a fitting plane. Different first curved surface sub-regions correspond to different fitting planes. Plane fitting is performed on the point cloud data of each first curved surface sub-region using a plane fitting algorithm. This algorithm includes, but is not limited to, the least squares method. The target point cloud data is the point cloud data corresponding to the stitching seams. The target point cloud data can be determined by filtering the point cloud data of the first curved surface sub-region using the fitting plane. For example, each fitting plane and the point cloud data of the first curved surface sub-region corresponding to that fitting plane can be input into a point cloud data filtering model for filtering, resulting in filtered point cloud data corresponding to multiple first curved surface sub-regions. These filtered point cloud data corresponding to multiple first curved surface sub-regions can then be used as the target point cloud data.
[0028] Specifically, the point cloud data of each first surface sub-region is fitted to a plane using the least squares method to obtain the fitting plane corresponding to each first surface sub-region. Each fitting plane and the point cloud data of the first surface sub-region corresponding to that fitting plane are input into the point cloud data filtering model for filtering, resulting in filtered point cloud data corresponding to multiple first surface sub-regions. The filtered point cloud data corresponding to multiple first surface sub-regions are used as target point cloud data, thus realizing the filtering of point cloud data of the first surface sub-regions. This can filter out the point cloud data corresponding to the stitching gaps, providing accurate data support for subsequent analysis and processing, and helping to reduce the computational workload of subsequent tasks.
[0029] Optionally, the point cloud data of the first surface sub-region is filtered based on the fitting plane to determine the target point cloud data, including: determining the distance and position information of the point cloud data of the first surface sub-region relative to the fitting plane based on the fitting plane and the point cloud data of the first surface sub-region; and filtering the point cloud data of the first surface sub-region based on the distance and position information to determine the target point cloud data.
[0030] The distance information refers to the vertical distance between the point cloud data of the first curved surface sub-region and the fitting plane. This distance information characterizes the proximity between the point cloud data of the first curved surface sub-region and the fitting plane. The distance information can be determined based on the point cloud data of the first curved surface sub-region and the fitting plane. For example, the point cloud data of the first curved surface sub-region and the fitting plane can be input into a distance determination model for processing to obtain the distance information of the point cloud data of the first curved surface sub-region relative to the fitting plane. The distance determination model includes, but is not limited to, neural network models and mathematical models. The position information refers to the orientation of the point cloud data of the first curved surface sub-region relative to the fitting plane. Optionally, the position information can be that the point cloud data of the first curved surface sub-region is above the fitting plane. Optionally, the position information can be that the point cloud data of the first curved surface sub-region is below the fitting plane. Optionally, the position information can be that the point cloud data of the first curved surface sub-region is on the fitting plane. The position information can be determined based on the fitting plane and the point cloud data of the first curved surface sub-region. For example, the point cloud data of the first curved surface sub-region and the fitted plane can be input into a position information determination model for processing to obtain the position information of the point cloud data of the first curved surface sub-region relative to the fitted plane. The position information determination model includes, but is not limited to, a neural network model. Alternatively, the point cloud data of the first curved surface sub-region can be substituted into the plane equation of the fitted plane to obtain a calculation result. The position information of the point cloud data of the first curved surface sub-region relative to the fitted plane is determined based on the sign of the calculation result. Here, the direction of the normal vector of the fitted plane is upward. When the calculation result is greater than zero, the position information is that the point cloud data of the first curved surface sub-region is above the fitted plane; when the calculation result is greater than zero, the position information is that the point cloud data of the first curved surface sub-region is below the fitted plane; and when the calculation result is greater than zero, the position information is that the point cloud data of the first curved surface sub-region is on the fitted plane. The point cloud data of the first curved surface sub-region can be filtered based on distance and position information. A first filtering condition can be preset. When the distance and position information meet the first filtering condition, the point cloud data of the first curved surface sub-region that meets the first filtering condition is used as the target point cloud data. The first filtering condition can be that the distance information of the point cloud data of the first curved surface sub-region relative to the fitting plane is greater than a preset distance threshold, and the position information of the point cloud data of the first curved surface sub-region relative to the fitting plane is that the point cloud data of the first curved surface sub-region is located below the fitting plane.
[0031] Specifically, the point cloud data of the first curved surface sub-region and the fitted plane are input into the distance determination model for processing to obtain the distance information of the point cloud data of the first curved surface sub-region relative to the fitted plane; the point cloud data of the first curved surface sub-region is substituted into the plane equation of the fitted plane to obtain the calculation result, and the position information of the point cloud data of the first curved surface sub-region relative to the fitted plane is determined according to the sign of the calculation result; filtering conditions are preset, and when the distance information and position information meet the filtering conditions, the point cloud data of the first curved surface sub-region that meets the filtering conditions is used as the target point cloud data, which realizes the filtering of the point cloud data of the first curved surface sub-region, provides accurate data support for subsequent analysis and processing, and helps to reduce the amount of computation in subsequent tasks.
[0032] S150. Determine the width information of the splicing gap based on the target point cloud data.
[0033] The width information represents the dimension of the splicing seam in the width direction. The width information of the splicing seam can be determined based on the target point cloud data. For example, the target point cloud data can be input into the width information determination model for processing to obtain the width information of the splicing seam. The width information determination model includes, but is not limited to, a neural network model. The width information determination model can be set according to requirements, and this invention does not impose any limitations.
[0034] Specifically, the target point cloud data is input into the width information determination model for processing to obtain the width information of the splicing gap. The width information of the splicing gap can be detected without stopping the automatic tape laying machine, which improves the detection efficiency and the accuracy of the splicing gap width information.
[0035] Optionally, the feature information of the bounding box of the target point cloud data is determined based on the target point cloud data; the size information of the bounding box is determined based on the feature information; and the width information of the splicing gap is determined based on the size information of the bounding box.
[0036] The bounding box is the circumscribed geometry of the target point cloud data, including but not limited to a rectangle. Optionally, the bounding box is the minimum bounding cuboid of the target point cloud data. Feature information describes the geometric properties of the bounding box. Optionally, feature information includes but is not limited to vertex coordinates. The feature information of the bounding box can be determined based on the target point cloud data. For example, the target point cloud data can be input into a bounding box feature determination model for processing to obtain the feature information of the bounding box. The bounding box feature determination model includes but is not limited to a neural network model. Size information is used to characterize the spatial span of the bounding box. For example, when the bounding box is the minimum bounding cuboid of the target point cloud data, the size information of the bounding box is the length, width, and height of the minimum bounding cuboid. The size information of the bounding box can be determined based on the feature information. For example, the feature information can be input into a size information determination model for processing to obtain the size information of the bounding box. The size information determination model includes but is not limited to a neural network model. The width information of the splicing gap can also be determined based on the size information of the bounding box. For example, the width in the size information of the bounding box can be used as the width information of the splicing gap.
[0037] Specifically, the target point cloud data is input into the bounding box feature determination model for processing to obtain the bounding box feature information; the feature information is input into the size information determination model for processing to obtain the size information of the bounding box; the width of the bounding box size information is used as the width information of the splicing gap, and the width information of the splicing gap can be detected without stopping the automatic tape laying machine, thus improving the detection efficiency and the accuracy of the width information of the splicing gap.
[0038] It should be noted that when the target point cloud data includes point cloud data corresponding to a single stitching seam, the width information of the stitching seam can be directly determined based on the target point cloud data. When the target point cloud data includes point cloud data corresponding to multiple stitching seams, clustering processing is required to obtain the target point cloud data corresponding to each stitching seam. For the target point cloud data corresponding to any stitching seam, the feature information of the bounding box corresponding to the target point cloud data of that stitching seam is determined based on the target point cloud data corresponding to the stitching seam; the size information of the bounding box corresponding to the target point cloud data of that stitching seam is determined based on the feature information of the bounding box corresponding to the target point cloud data of that stitching seam; and the width information of the stitching seam is determined based on the size information of the bounding box corresponding to the target point cloud data of that stitching seam.
[0039] Optionally, the method further includes: downsampling the point cloud data of the target region to obtain downsampled point cloud data; segmenting the downsampled point cloud data based on region segmentation information to obtain point cloud data of multiple second surface sub-regions; performing plane fitting on the point cloud data of each second surface sub-region to obtain the fitting plane corresponding to the second surface sub-region; filtering the point cloud data of the first surface sub-region based on the fitting plane corresponding to the second surface sub-region to determine the target point cloud data; and determining the width information of the splicing gap based on the target point cloud data.
[0040] The process involves downsampling the point cloud data of the target region. Downsampling methods, including but not limited to voxel mesh methods, can effectively reduce the amount of point cloud data in the target region, thus improving data processing efficiency. The second surface sub-region is a region obtained by segmenting the target region. Different second surface sub-regions have different curvatures. Each second surface sub-region includes the corresponding downsampled point cloud data. Segmenting the downsampled point cloud data based on region segmentation information can be achieved by dividing the target region into multiple equal parts, each including the corresponding downsampled point cloud data. These segmented regions are the second surface sub-regions. The second surface sub-regions correspond one-to-one with the first surface sub-regions. The first surface sub-regions have the same area and location. Plane fitting is performed on the point cloud data of each second surface sub-region using plane fitting algorithms, including but not limited to the least squares method. The fitting plane corresponding to the second surface sub-region can be represented by a plane expression, for example, by a plane equation.
[0041] The target point cloud data can also be determined by filtering the point cloud data of the first surface sub-region using the fitting plane corresponding to the second surface sub-region. For example, the fitting plane corresponding to each second surface sub-region and the point cloud data of the first surface sub-region corresponding to that fitting plane can be input into the point cloud data filtering model for filtering, resulting in filtered point cloud data corresponding to multiple first surface sub-regions. The filtered point cloud data corresponding to multiple first surface sub-regions can then be used as the target point cloud data.
[0042] Specifically, the point cloud data of the target region is downsampled using the voxel grid method to obtain downsampled point cloud data; the target region is equally divided according to the region segmentation information to obtain multiple second-surface sub-regions; the point cloud data of the second-surface sub-regions is fitted to a plane using the least squares method to obtain the fitting plane corresponding to the second-surface sub-region; the fitting plane corresponding to each second-surface sub-region and the point cloud data of the first-surface sub-region corresponding to the fitting plane are input into the point cloud data filtering model for filtering to obtain the filtered point cloud data corresponding to each of the multiple first-surface sub-regions. According to the method, the filtered point cloud data corresponding to multiple first curved surface sub-regions are used as target point cloud data. The target point cloud data is input into the width information determination model for processing to obtain the width information of the splicing gap. The width information of the splicing gap can be detected without stopping the automatic tape laying machine, which improves the detection efficiency and the accuracy of the splicing gap width information. At the same time, by filtering the point cloud data of the first curved surface sub-regions through downsampling point cloud data, the number of point cloud data in the target area can be effectively reduced, which is conducive to improving the detection efficiency of splicing gap.
[0043] The technical solution of this embodiment acquires point cloud data of the target region, including stitching seams, providing comprehensive data support for subsequent analysis and processing, ensuring efficient and accurate execution of subsequent tasks; it determines region segmentation information based on the directional information corresponding to the point cloud data of the target region, providing accurate data support for the segmentation of the point cloud data of the target region; based on the region segmentation information, it segments the point cloud data of the target region to obtain point cloud data of multiple first curved surface sub-regions, realizing the segmentation of the target region and its point cloud data, providing a refined data foundation for subsequent analysis and processing; for each first curved surface... The point cloud data of the surface region is fitted with a plane to obtain the fitting plane corresponding to each first curved surface region. Based on the fitting plane, the point cloud data of the first curved surface region is filtered to determine the target point cloud data. This filtering of the point cloud data of the first curved surface region can identify the point cloud data corresponding to the splicing gap, providing accurate data support for subsequent analysis and processing, and helping to reduce the computational workload of subsequent tasks. Based on the target point cloud data, the width information of the splicing gap can be determined without stopping the automatic tape laying machine, thus improving the detection efficiency and accuracy of the splicing gap width information.
[0044] Figure 3This is a flowchart of another splicing gap detection method provided by an embodiment of the present invention. This embodiment is a refinement of the above embodiments. Based on the foregoing embodiments, it provides a detailed explanation of determining region segmentation information based on the direction information corresponding to the point cloud data of the target region. For specific implementation details, please refer to the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 3 As shown, the method specifically includes the following steps: S210. Obtain point cloud data of the target area, including the stitching seams within the target area.
[0045] S220. Project the point cloud data of the target region onto the length direction corresponding to the point cloud data of the target region to obtain first projection data; project the point cloud data of the target region onto the width direction corresponding to the point cloud data of the target region to obtain second projection data; determine the region segmentation information of the point cloud data of the target region based on the first projection data and the second projection data.
[0046] The first projection data represents the distribution of point cloud data in the target region along its length. This first projection data is obtained by projecting the point cloud data of the target region along its length. For example, the length direction corresponding to the point cloud data of the target region can be used as the first projection axis, and a plane perpendicular to the length direction can be used as the first projection surface. Projecting the point cloud data of the target region onto the first projection surface yields the first projection data corresponding to the point cloud data of the target region. The second projection data represents the distribution of point cloud data in the target region along its width. This second projection data is obtained by projecting the point cloud data of the target region along its width. For example, the width direction corresponding to the point cloud data of the target region can be used as the second projection axis, and a plane perpendicular to the width direction can be used as the second projection surface. Projecting the point cloud data of the target region onto the second projection surface yields the second projection data corresponding to the point cloud data of the target region. Region segmentation information can also be determined based on the first and second projection data. For example, the first and second projection data can be input into a region segmentation information determination model for processing to obtain region segmentation information. The region segmentation information determination model includes, but is not limited to, neural network models and mathematical models.
[0047] Specifically, the length direction corresponding to the point cloud data of the target region is used as the first projection axis, and the plane perpendicular to the length direction is used as the first projection surface. The point cloud data of the target region is projected onto the first projection surface to obtain the first projection data corresponding to the point cloud data of the target region. The width direction corresponding to the point cloud data of the target region is used as the second projection axis, and the plane perpendicular to the length direction is used as the second projection surface. The point cloud data of the target region is projected onto the second projection surface to obtain the second projection data corresponding to the point cloud data of the target region. The first and second projection data are input into the region segmentation information determination model for processing to obtain region segmentation information, which provides accurate data support for the segmentation of the point cloud data of the target region.
[0048] Optionally, determining the region segmentation information of the point cloud data of the target region based on the first projection data and the second projection data includes: performing arc fitting processing on the first projection data to obtain the first geometric feature data of the first arc; performing arc fitting processing on the second projection data to obtain the second geometric feature data of the second arc; and determining the region segmentation information of the point cloud data of the target region based on the first geometric feature data and the second geometric feature data.
[0049] The first arc is obtained by fitting the first projection data to an arc. An arc fitting algorithm can be used to fit the first projection data to an arc, including but not limited to the least squares method. The first geometric feature data includes at least one of the following: the center position, fitting radius, arc length, and central angle of the first arc. The second arc is obtained by fitting the second projection data to an arc. An arc fitting algorithm can be used to fit the second projection data to an arc, including but not limited to the least squares method. The second geometric feature data includes at least one of the following: the center position, fitting radius, arc length, and central angle of the second arc. Region segmentation information can also be determined based on the first and second geometric feature data. For example, the first and second geometric feature data can be input into a region segmentation information determination model for processing to obtain the region segmentation information of the point cloud data of the target region. The region segmentation information determination model includes, but is not limited to, neural network models and mathematical models.
[0050] Specifically, the first geometric feature data of the first arc is obtained by fitting the first projection data with a circular arc using the least squares method; the second geometric feature data of the second arc is obtained by fitting the second projection data with a circular arc using the least squares method; the first geometric feature data and the second geometric feature data are input into the region segmentation information determination model for processing to obtain the region segmentation information of the point cloud data of the target region, providing accurate data support for the segmentation of the point cloud data of the target region.
[0051] For example, the formula for calculating region segmentation information is as follows: ; in, This indicates the number of equal divisions along the length direction of the point cloud data in the target area; This indicates the arc length of the second arc; This represents the fitted radius of the second arc; This represents a preset fitting radius threshold, which can be set according to requirements; this invention does not impose any limitations on it. This indicates the number of equal divisions along the width direction of the point cloud data in the target area; This indicates the arc length of the first arc; This represents the fitted radius of the first arc.
[0052] S230. Based on the region segmentation information, the point cloud data of the target region is segmented to obtain point cloud data of multiple first surface sub-regions.
[0053] S240. Perform plane fitting on the point cloud data of each first surface sub-region to obtain the fitting plane corresponding to each first surface sub-region; filter the point cloud data of the first surface sub-region based on the fitting plane to determine the target point cloud data.
[0054] S250. Determine the width information of the splicing gap based on the target point cloud data.
[0055] Because the target point cloud data may contain noisy point cloud data, which affects the detection of the width of the splicing gap, resulting in low accuracy of the splicing gap width information, it is necessary to filter the target point cloud data.
[0056] Optionally, before determining the width information of the splicing gap based on the target point cloud data, the method further includes: projecting the target point cloud data onto the target point cloud data based on the width direction corresponding to the point cloud data of the target region to obtain third projection data; performing clustering processing on the third projection data to obtain target projection data; and filtering the target point cloud data based on the target projection data to obtain filtered target point cloud data.
[0057] The third projection data represents the distribution of the target point cloud data along the width direction. This third projection data is obtained by projecting the target point cloud data along the width direction. For example, the width direction corresponding to the point cloud data of the target region can be used as the third projection axis, and a plane perpendicular to the width direction can be used as the third projection plane. Projecting the target point cloud data onto this third projection plane yields the corresponding third projection data. See also [example description]. Figure 4 , Figure 4This is a schematic diagram of a third projection data provided in an embodiment of the present invention. Clustering processing of the third projection data can be performed using a clustering algorithm, including but not limited to density-based spatial clustering of applications with noise (DBSCAN). The target projection data is the projection data corresponding to the stitching gaps in the third projection data. The filtering process for the target point cloud data is as follows: establishing a mapping relationship between the target projection data and the corresponding point cloud data in the target point cloud data; retaining the point cloud data in the target point cloud data that satisfies the above mapping relationship; and removing the point cloud data in the target point cloud data that does not satisfy the above mapping relationship, thus obtaining the filtered target point cloud data.
[0058] Specifically, the width direction of the point cloud data of the target area is used as the third projection axis, and the plane perpendicular to the width direction is used as the third projection plane. The target point cloud data is projected onto the third projection plane to obtain the third projection data corresponding to the target point cloud data. The third projection data is clustered using the DBSCAN algorithm to obtain the target projection data. A mapping relationship is established between the target projection data and the corresponding point cloud data in the target point cloud data. Point cloud data that satisfy the above mapping relationship is retained, and point cloud data that do not satisfy the above mapping relationship are removed to obtain the filtered target point cloud data. This achieves the filtering of target point cloud data, reduces the influence of noisy point cloud data on the width information of the splicing gap, and helps to improve the accuracy of the width information of the splicing gap.
[0059] The technical solution of this embodiment, by acquiring point cloud data of the target area, including the stitching gaps within the target area, provides comprehensive data support for subsequent analysis and processing, ensuring that subsequent tasks can be executed efficiently and accurately; Projecting the point cloud data of the target region along its length direction yields first projection data. Projecting it along its width direction yields second projection data. Based on these two projections, region segmentation information for the target region's point cloud data is determined, providing accurate data support for segmentation. Segmenting the target region's point cloud data using this region segmentation information results in multiple first-curved sub-regions, achieving segmentation of the target region and its point cloud data. This provides a refined data foundation for subsequent analysis and processing. The system employs a multi-dimensional algorithm: First, it performs planar fitting on the point cloud data of each first-curved surface sub-region to obtain a corresponding fitting plane. Based on this fitting plane, it filters the point cloud data of the first-curved surface sub-region to determine the target point cloud data. This filtering process effectively identifies the point cloud data corresponding to the splicing seams, providing accurate data support for subsequent analysis and processing, and reducing the computational load of subsequent tasks. Second, it determines the width information of the splicing seams based on the target point cloud data, eliminating the need to stop the automatic tape-laying machine and improving the detection efficiency and accuracy of the seam width information.
[0060] Figure 5 This is a schematic diagram of a splicing gap detection device provided in an embodiment of the present invention. Figure 5 As shown, the device includes a point cloud data acquisition module 310, a region segmentation information determination module 320, a point cloud data segmentation module 330, a target point cloud data determination module 340, and a width information determination module 350.
[0061] The system includes: a point cloud data acquisition module 310 for acquiring point cloud data of a target region, including splicing seams; a region segmentation information determination module 320 for determining region segmentation information based on the orientation information corresponding to the point cloud data of the target region; a point cloud data segmentation module 330 for segmenting the point cloud data of the target region based on the region segmentation information to obtain point cloud data of multiple first curved surface sub-regions; a target point cloud data determination module 340 for performing plane fitting on the point cloud data of each first curved surface sub-region to obtain the fitting plane corresponding to the first curved surface sub-region; filtering the point cloud data of the first curved surface sub-region based on the fitting plane to determine the target point cloud data; and a width information determination module 350 for determining the width information of the splicing seams based on the target point cloud data.
[0062] The technical solution of this embodiment acquires point cloud data of a target region through a point cloud data acquisition module. This target region includes stitching seams, providing comprehensive data support for subsequent analysis and processing, ensuring efficient and accurate execution of subsequent tasks. A region segmentation information determination module determines region segmentation information based on the direction information corresponding to the point cloud data of the target region, providing accurate data support for the segmentation of the point cloud data of the target region. A point cloud data segmentation module segments the point cloud data of the target region based on the region segmentation information, obtaining point cloud data of multiple first-curved surface sub-regions. This achieves the segmentation of the target region and its point cloud data, providing a refined data foundation for subsequent analysis and processing. The target point cloud data determination module performs planar fitting on the point cloud data of each first curved surface sub-region to obtain the fitting plane corresponding to the first curved surface sub-region. Based on the fitting plane, the point cloud data of the first curved surface sub-region is filtered to determine the target point cloud data. This achieves the filtering of point cloud data of the first curved surface sub-region, which can filter out the point cloud data corresponding to the splicing gap, providing accurate data support for subsequent analysis and processing, and helping to reduce the computational workload of subsequent tasks. The width information determination module determines the width information of the splicing gap based on the target point cloud data. The width information of the splicing gap can be detected without stopping the automatic tape laying machine, which improves the detection efficiency and the accuracy of the width information of the splicing gap.
[0063] Based on the above embodiments, optionally, the direction information corresponding to the point cloud data of the target area includes the length direction and width direction corresponding to the point cloud data of the target area.
[0064] Optionally, the region segmentation information determination module 320 is further configured to: project the point cloud data of the target region based on the length direction corresponding to the point cloud data of the target region to obtain first projection data; project the point cloud data of the target region based on the width direction corresponding to the point cloud data of the target region to obtain second projection data; and determine the region segmentation information of the point cloud data of the target region based on the first projection data and the second projection data.
[0065] Optionally, the region segmentation information determination module 320 is further configured to: perform arc fitting processing on the first projection data to obtain the first geometric feature data of the first arc; perform arc fitting processing on the second projection data to obtain the second geometric feature data of the second arc; and determine the region segmentation information of the point cloud data of the target region based on the first geometric feature data and the second geometric feature data.
[0066] Optionally, the device further includes a target point cloud data filtering module, used to: before determining the width information of the splicing gap based on the target point cloud data, project the target point cloud data based on the width direction corresponding to the point cloud data of the target area to obtain third projection data; perform clustering processing on the third projection data to obtain target projection data; and filter the target point cloud data based on the target projection data to obtain filtered target point cloud data.
[0067] Optionally, the target point cloud data determination module 340 is further configured to: determine the distance and position information of the point cloud data of the first surface sub-region relative to the fitting plane based on the point cloud data of the fitting plane and the first surface sub-region; and filter the point cloud data of the first surface sub-region based on the distance and position information to determine the target point cloud data.
[0068] Optionally, the width information determination module 350 is also used to: determine the feature information of the bounding box of the target point cloud data based on the target point cloud data; determine the size information of the bounding box based on the feature information; and determine the width information of the splicing gap based on the size information of the bounding box.
[0069] Optionally, the width information determination module 350 is further configured to: perform downsampling processing on the point cloud data of the target region to obtain downsampled point cloud data; perform segmentation processing on the downsampled point cloud data based on the region segmentation information to obtain point cloud data of multiple second surface sub-regions; perform plane fitting on the point cloud data of each second surface sub-region to obtain the fitting plane corresponding to the second surface sub-region; filter the point cloud data of the first surface sub-region based on the fitting plane corresponding to the second surface sub-region to determine the target point cloud data; and determine the width information of the splicing gap based on the target point cloud data.
[0070] The splicing gap detection device provided in this embodiment of the invention can execute the splicing gap detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.
[0071] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0072] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0073] Multiple components in electronic device 10 are connected to input / output (I / O) interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0074] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a splicing gap detection method.
[0075] In some embodiments, a seam detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the seam detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a seam detection method by any other suitable means (e.g., by means of firmware).
[0076] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.
[0077] A computer program for implementing a splice gap detection method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer program causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0078] This invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a splicing gap detection method, the method comprising: The process involves: acquiring point cloud data of the target region, including the stitching seams; determining region segmentation information based on the orientation information corresponding to the point cloud data of the target region; segmenting the point cloud data of the target region based on the region segmentation information to obtain point cloud data of multiple first-curved sub-regions; performing planar fitting on the point cloud data of each first-curved sub-region to obtain the fitting plane corresponding to each first-curved sub-region; filtering the point cloud data of the first-curved sub-regions based on the fitting plane to determine the target point cloud data; and determining the width information of the stitching seams based on the target point cloud data.
[0079] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0080] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0081] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0082] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0083] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for detecting seam gaps in splicing, characterized in that, include: Acquire point cloud data of a target area, including stitching seams within the target area; Region segmentation information is determined based on the directional information corresponding to the point cloud data of the target region; Based on the region segmentation information, the point cloud data of the target region is segmented to obtain point cloud data of multiple first surface sub-regions; Plane fitting is performed on the point cloud data of each first surface sub-region to obtain the fitting plane corresponding to each first surface sub-region; the point cloud data of the first surface sub-region is filtered based on the fitting plane to determine the target point cloud data. The width information of the splicing gap is determined based on the target point cloud data.
2. The method according to claim 1, characterized in that, The directional information corresponding to the point cloud data of the target area includes the length direction and the width direction corresponding to the point cloud data of the target area; The determination of region segmentation information based on the directional information corresponding to the point cloud data of the target region includes: Projecting the point cloud data of the target region onto the point cloud data of the target region based on the length direction corresponding to the point cloud data of the target region, to obtain the first projection data; Projecting the point cloud data of the target region onto the point cloud data of the target region in the width direction yields second projection data. Based on the first projection data and the second projection data, the region segmentation information of the point cloud data of the target region is determined.
3. The method according to claim 2, characterized in that, The method for determining the region segmentation information of the point cloud data of the target region based on the first projection data and the second projection data includes: Perform circular arc fitting processing on the first projection data to obtain the first geometric feature data of the first circular arc; The second projection data is subjected to arc fitting processing to obtain the second geometric feature data of the second arc; The region segmentation information of the point cloud data of the target region is determined based on the first geometric feature data and the second geometric feature data.
4. The method according to claim 2, characterized in that, Before determining the width information of the splicing gap based on the target point cloud data, the method further includes: The target point cloud data is projected onto the target point cloud data based on the width direction corresponding to the target region to obtain third projection data; Clustering is performed on the third projection data to obtain the target projection data; The target point cloud data is filtered based on the target projection data to obtain the filtered target point cloud data.
5. The method according to claim 1, characterized in that, The step of filtering the point cloud data of the first surface sub-region based on the fitted plane to determine the target point cloud data includes: Based on the fitted plane and the point cloud data of the first surface sub-region, determine the distance and position information of the point cloud data of the first surface sub-region relative to the fitted plane; The point cloud data of the first curved surface sub-region is filtered based on the distance information and the location information to determine the target point cloud data.
6. The method according to claim 1, characterized in that, Determining the width information of the splicing gap based on the target point cloud data includes: Based on the target point cloud data, determine the feature information of the bounding box of the target point cloud data; The size information of the bounding box is determined based on the feature information; The width of the splicing gap is determined based on the size information of the enclosure.
7. The method according to claim 1, characterized in that, The method further includes: The point cloud data of the target area is downsampled to obtain downsampled point cloud data. Based on the region segmentation information, the downsampled point cloud data is segmented to obtain point cloud data of multiple second surface sub-regions; Perform plane fitting on the point cloud data of each second surface sub-region to obtain the fitting plane corresponding to the second surface sub-region; filter the point cloud data of the first surface sub-region based on the fitting plane corresponding to the second surface sub-region to determine the target point cloud data. The width information of the splicing gap is determined based on the target point cloud data.
8. A splicing gap detection device, characterized in that, include: A point cloud data acquisition module is used to acquire point cloud data of a target area, including splicing seams within the target area. The region segmentation information determination module is used to determine region segmentation information based on the directional information corresponding to the point cloud data of the target region. The point cloud data segmentation module is used to segment the point cloud data of the target region based on the region segmentation information to obtain point cloud data of multiple first surface sub-regions. The target point cloud data determination module is used to perform plane fitting on the point cloud data of each first surface sub-region to obtain the fitting plane corresponding to the first surface sub-region; and to filter the point cloud data of the first surface sub-region based on the fitting plane to determine the target point cloud data. The width information determination module is used to determine the width information of the splicing gap based on the target point cloud data.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the splice gap detection method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the splicing gap detection method according to any one of claims 1-7.