Point cloud matching-based welded seam size measurement method and system, medium, and device

Abstract

A point cloud matching-based welded seam size measurement method, comprising: acquiring first point cloud data of a region to be welded before welding acquired by means of a three-dimensional laser scanner and second point cloud data of a welded region after welding acquired by means of the three-dimensional laser scanner (10); on the basis of the first point cloud data and the region to be welded, determining point cloud data of a region of interest to be welded (20); on the basis of the second point cloud data and the welded region, determining point cloud data of a welded region of interest (30); matching the point cloud data of the welding region of interest and the point cloud data of the welded region of interest, to obtain a matching result (40); according to the matching result, extracting a welded seam point cloud set (50); on the basis of a point cloud principal component analysis method, analyzing the welded seam point cloud set, to obtain welded seam sizes (60). The efficiency and accuracy of rebar welded seam measurement can be improved. Further disclosed are a point cloud matching-based welded seam size detection system, a computer-readable storage medium, and an electronic device.

Description

Weld size detection method, system, medium and equipment based on point cloud matching

[0001] Technical Field

[0002] The present application relates to the technical field of building engineering construction, and specifically to a weld size detection method, system, medium and equipment based on point cloud matching. Background Art

[0003] Rebar is widely used in the construction of national infrastructure, including roads, buildings, and bridges. This is particularly true in the fabrication and construction of rebar cages for underground diaphragm walls. Rebar is woven into a cage-like structure according to design requirements to reinforce and support the wall. Its primary function is to enhance the wall's mechanical properties, including bending, shear, and compression, ensuring its stability and safety. The primary method of connecting the rebar is welding, and the quality of the welds determines the performance of the rebar cage and, consequently, the safety and stability of the entire cage.

[0004] The weld size of steel bars is an important criterion for judging weld quality. The traditional weld inspection method is the appearance inspection method, which mainly uses manual measurement with an inspection ruler. This method is easily affected by the subjective influence of the inspectors, resulting in inconsistent inspection standards and inaccurate inspection results. Summary of the Invention

[0005] The present application provides a weld size detection method, system, medium and equipment based on point cloud matching, which can improve the efficiency and accuracy of steel bar weld detection, thereby ensuring the safety and stability of the entire steel cage.

[0006] In a first aspect, the present application provides a weld size detection method based on point cloud matching, the method comprising:

[0007] Acquire first point cloud data of the area to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of the welded area after welding collected by the three-dimensional laser scanner;

[0008] Determining point cloud data of an area of ​​interest to be welded based on the first point cloud data and the area to be welded;

[0009] Determining point cloud data of a welded area of ​​interest based on the second point cloud data and the welded area;

[0010] Performing point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result;

[0011] Extracting a weld point cloud set according to the matching result;

[0012] The weld point cloud set is analyzed based on a point cloud principal component analysis method to obtain the dimensions of each weld.

[0013] By adopting the above technical solution, a three-dimensional laser scanner is used to collect the first point cloud data of the area to be welded before welding and the second point cloud data of the welded area after welding, and the point cloud data of the area of ​​interest to be welded and the point cloud data of the welded area of ​​interest are determined. The point cloud data of the welding area of ​​interest is matched with the point cloud data of the welded area of ​​interest. The weld point cloud set is extracted according to the matching result, and then the weld point cloud set is analyzed based on the point cloud principal component analysis method to obtain the size of each weld. Compared with the existing technology, the subjective influencing factors of manual measurement can be reduced, and at the same time, the detection accuracy and efficiency of the weld can be effectively improved.

[0014] Optionally, obtaining first point cloud data of the area to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of the welded area after welding collected by the three-dimensional laser scanner, includes: adjusting the posture of the three-dimensional laser scanner according to the weld in the area to be welded so that the weld in the area to be welded is within the measurement range of the three-dimensional laser scanner; obtaining the first point cloud data of the area to be welded collected by the three-dimensional laser scanner; adjusting the posture of the three-dimensional laser scanner according to the weld in the welded area so that the weld in the welded area is within the measurement range of the three-dimensional laser scanner; obtaining the second point cloud data of the welded area collected by the three-dimensional laser scanner.

[0015] By adopting the above technical solution, the posture of the 3D laser scanner is adjusted according to the adaptability of the weld, so that the welds in the area to be welded and the welds in the welded area are both within the measurement range of the 3D laser scanner, thereby improving the quality and efficiency of the weld point cloud data detection.

[0016] Optionally, the method of determining the point cloud data of the area of ​​interest to be welded based on the first point cloud data and the area to be welded also includes: denoising and downsampling the first point cloud data to obtain first target point cloud data; estimating the first maximum value set and the first minimum value set of the weld coordinates in the area to be welded in the three-dimensional coordinate direction; and determining the point cloud data of the area of ​​interest to be welded based on the first maximum value set, the first minimum value set and the first target point cloud data.

[0017] By adopting the above technical solution, the first point cloud data is denoised and downsampled, which can remove noise and redundant information, reduce the amount of point cloud data, and estimate the first maximum value set and the first minimum value set of the weld coordinates in the area to be welded in the three-dimensional coordinate direction, so that the area to be welded can be refined and controlled, further improving the accuracy and efficiency of the detection of the area to be welded.

[0018] Optionally, the point cloud data of the welded area of ​​interest is determined based on the second point cloud data and the welded area, including: denoising and downsampling the second point cloud data to obtain second target point cloud data; estimating the second maximum value set and the second minimum value set of the weld coordinates in the welded area in the three-dimensional coordinate direction; and determining the point cloud data of the welded area of ​​interest based on the second maximum value set, the second minimum value set and the second target point cloud data.

[0019] By adopting the above technical solution, the second point cloud data is denoised and downsampled, which can remove noise and redundant information, reduce the amount of point cloud data, and estimate the second maximum value set and second minimum value set of the weld coordinates in the welded area in the three-dimensional coordinate direction. The welded area can be refined and controlled, further improving the accuracy and efficiency of the detection of the welded area.

[0020] Optionally, performing point cloud matching on the point cloud data of the welding area of ​​interest with the point cloud data of the welded area of ​​interest to obtain a matching result includes: based on an iterative nearest point method, performing point cloud matching on the point cloud data of the area of ​​interest to be welded with the point cloud data of the welded area of ​​interest, and calculating a posture transformation matrix; and using the posture transformation matrix as the matching result.

[0021] By adopting the above technical solution, the point cloud data of the welding area of ​​interest is matched with the point cloud data of the welded area of ​​interest, and the point cloud data of the two areas are merged into a whole. By calculating the posture transformation matrix, alignment and matching between the point clouds can be achieved, so that the welded area can be processed and analyzed subsequently, and the accuracy and efficiency of the detection of the welded area can be improved.

[0022] Optionally, extracting the weld point cloud set based on the matching result includes: converting the point cloud data of the welded area of ​​interest to the area of ​​interest to be welded based on the posture transformation matrix in the matching result; for any target point in the welded area of ​​interest: determining the point cloud data with the shortest Euclidean distance to the target point in the point cloud data of the area of ​​interest to be welded, and taking the point corresponding to the point cloud data of the welded area in the area of ​​interest to be welded whose shortest Euclidean distance is greater than the weld extraction threshold as the weld point to obtain the weld point cloud set.

[0023] By adopting the above technical solution, the point cloud data with the shortest distance is determined in the point cloud data of the area of ​​interest to be welded through Euclidean distance, and the point with the shortest distance is set as the weld point. Euclidean distance is the distance between points and is an important indicator for evaluating the matching and registration effect of point cloud data. The point corresponding to the point cloud data of the welded area with the shortest Euclidean distance greater than the weld extraction threshold is used as the weld point. The extraction progress and number of weld points can be controlled, effectively improving the subsequent detection accuracy and efficiency of the weld.

[0024] Optionally, after analyzing the weld point cloud set based on the point cloud principal component analysis method to obtain the size of each weld, it includes: comparing the size of each weld with a preset standard weld size range, the weld size includes length, width and depth; determining the weld whose size does not meet the preset standard weld size range as an unqualified weld; and determining the weld whose size meets the preset standard weld size range as a qualified weld.

[0025] By adopting the above technical solution, the measured weld size is compared with the preset standard weld size range to obtain the weld inspection results, so that personnel can clearly know whether the weld is compliant, thereby facilitating subsequent weld inspection and acceptance.

[0026] In a second aspect of the present application, a weld size detection system based on point cloud matching is provided, the system comprising:

[0027] a point cloud data acquisition module, configured to acquire first point cloud data of the area to be welded before welding, acquired by a three-dimensional laser scanner, and second point cloud data of the welded area after welding, acquired by the three-dimensional laser scanner;

[0028] An area of ​​interest acquisition module is configured to determine point cloud data of an area of ​​interest to be welded based on the first point cloud data and the area to be welded; and to determine point cloud data of an area of ​​interest to be welded based on the second point cloud data and the welded area;

[0029] a point cloud matching module, configured to perform point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result;

[0030] A weld point cloud set extraction module, used for extracting weld point cloud sets according to the matching results;

[0031] A test report generation module is used to analyze the weld point cloud set based on a point cloud principal component analysis method to obtain the dimensions of each weld;

[0032] The weld size generation module is used to analyze the weld point cloud set based on the point cloud principal component analysis method to obtain the size of each weld.

[0033] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0034] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0035] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0036] 1. This application uses a three-dimensional laser scanner to collect first point cloud data of the area to be welded before welding and second point cloud data of the welded area after welding, and determines the point cloud data of the area of ​​interest to be welded and the point cloud data of the welded area of ​​interest. The point cloud data of the welding area of ​​interest is matched with the point cloud data of the welded area of ​​interest. The weld point cloud set is extracted based on the matching results, and then the weld point cloud set is analyzed based on the point cloud principal component analysis method to obtain the dimensions of each weld. Compared with the existing technology, this can reduce the subjective influence factors of manual measurement and effectively improve the detection accuracy and efficiency of the weld.

[0037] 2. This application performs point cloud matching on the point cloud data of the welding area of ​​interest and the point cloud data of the welded area of ​​interest, merges the point cloud data of the two areas into a whole, and calculates the pose transformation matrix to achieve alignment and matching between the point clouds, so as to facilitate subsequent processing and analysis of the welded area, thereby improving the accuracy and efficiency of detection of the welded area.

[0038] 3. In this application, the measured weld size is compared with the preset standard weld size range to obtain the weld inspection results, so that personnel can clearly know whether the weld is compliant, thereby facilitating subsequent weld inspection and acceptance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] FIG1 is a schematic flow chart of a weld size detection method based on point cloud matching provided in an embodiment of the present application;

[0040] FIG2 is a schematic diagram of a weld inspection performed by a three-dimensional laser scanner according to an embodiment of the present application;

[0041] FIG3 is a module schematic diagram of a weld size detection system based on point cloud matching provided in an embodiment of the present application;

[0042] FIG4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.

[0043] Explanation of the accompanying symbols: 301, point cloud data acquisition module; 302, region of interest acquisition module; 303, point cloud matching module; 304, weld point cloud set extraction module; 305, weld size generation module; 400, electronic device; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0045] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0046] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0047] In order to facilitate understanding of the method and system provided by the embodiments of the present application, before introducing the embodiments of the present application, the background of the embodiments of the present application is first introduced.

[0048] Rebar is essential in construction. Steel mills can't produce enough steel to meet all building needs, so contractors often weld steel to meet their needs, either in length or strength. This practice is common, saving costs and improving material utilization. This is especially true in the fabrication and construction of rebar cages for underground continuous walls, where the rebar is braided and welded into a cage-like structure according to design requirements. This structure is used to reinforce and support the underground continuous wall.

[0049] The welding quality of steel bars determines the safety and stability of the entire steel cage, and the weld size of the steel bars is an important criterion for judging the weld quality. The traditional weld detection method mainly adopts the manual appearance inspection method, which uses a detection ruler to perform manual measurement and then manually observe and judge. This method of weld detection is easily affected by the subjective influence of personnel, resulting in inaccurate weld detection results.

[0050] In one embodiment, referring to FIG1 , a flow chart of a method for detecting weld size based on point cloud matching is provided. This method can be implemented using a computer program, a single-chip microcomputer, or a weld size detection system based on point cloud matching. The computer program can be integrated into an application or run as an independent tool application. Specifically, in this embodiment of the present application, the method can be applied to a controller of a photographic light. The method includes steps 10 to 60, which are as follows:

[0051] Step 10: Acquire first point cloud data of the area to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of the welded area after welding collected by a three-dimensional laser scanner.

[0052] A 3D laser scanner is a measuring device that uses the principle of laser ranging to obtain three-dimensional coordinate information by scanning an object's surface. It can quickly and accurately obtain three-dimensional shape information of an object's surface. Its operating principle is: a laser beam is emitted, irradiated by the surface, and then reflected back. The 3D laser scanner receives the reflected laser signal and calculates the distance information to the object's surface based on the time delay of the signal, thereby obtaining the object's three-dimensional coordinate information. In the embodiments of this application, a 3D laser scanner is used to inspect welds.

[0053] Point cloud data is a collection of data in a three-dimensional space composed of a large number of points, each of which contains its position in space and possibly other attributes. Point cloud data can represent information such as the shape, texture, and surface features of an object or scene. In the embodiments of the present application, the point cloud data can be acquired by a 3D laser scanner, wherein the first point cloud data refers to the data set acquired by the 3D laser scanner from the area to be welded before welding, and the second point cloud data refers to the data set acquired by the 3D laser scanner from the welded area.

[0054] Based on the above embodiment, as an optional embodiment, the step of acquiring first point cloud data of the area to be welded before welding collected by a 3D laser scanner and second point cloud data of the welded area after welding collected by a 3D laser scanner may further include the following steps:

[0055] Step 101: adjusting the posture of the 3D laser scanner according to the weld in the area to be welded, so that the weld in the area to be welded is within the measurement range of the 3D laser scanner.

[0056] Step 102: Acquire first point cloud data of the area to be welded collected by a three-dimensional laser scanner.

[0057] Specifically, before welding, a 3D laser scanner is installed in the area to be welded. The 3D laser scanner is wirelessly connected to the computer device. Before measuring, the 3D laser scanner is debugged and calibrated to determine the parameters such as the measuring range, scanning speed and scanning resolution of the 3D laser scanner. Generally speaking, the scanning range and speed should be adjusted according to the size and shape of the area to be measured to ensure the comprehensiveness and efficiency of the scan. Before measuring, the posture of the 3D laser scanner is adjusted according to the welds in the area to be welded so that the welds in the area to be welded are within the measuring range of the 3D laser scanner. During scanning, it is necessary to ensure that the distance and angle between the 3D laser scanner and the area to be measured are appropriate to ensure the comprehensiveness and overlap of the scan. The specific adjustment parameters can be adjusted by the personnel themselves.

[0058] Furthermore, after adjusting the various parameters, the 3D laser scanner is controlled to start working. According to the data collected by the 3D laser scanner, the first point cloud data of the area to be welded is generated based on the 3D reconstruction software or point cloud processing software. The first point cloud data is 3D data composed of a large number of points, which can reflect the shape and characteristics of the area to be welded.

[0059] Step 103: Adjust the position of the 3D laser scanner according to the weld in the welded area so that the weld in the welded area is within the measurement range of the 3D laser scanner.

[0060] Step 104: Acquire second point cloud data of the welded area collected by the 3D laser scanner.

[0061] Specifically, a 3D laser scanner is mounted on the welded area, and the position of the 3D laser scanner is adjusted based on the welds in the welded area so that the welds in the welded area are within the measurement range of the 3D laser scanner. The specific implementation process can be referred to in step 101 above and will not be repeated here. The 3D laser scanner is controlled to start operating, and based on the data collected by the 3D laser scanner, second point cloud data of the area to be welded is generated using 3D reconstruction software or point cloud processing software. The second point cloud data is 3D data composed of a large number of points and can reflect the shape and characteristics of the welded area.

[0062] Step 20: Based on the first point cloud data and the area to be welded, determine the point cloud data of the area of ​​interest to be welded.

[0063] Because a 3D laser scanner can scan a large area and potentially overlap, the first point cloud data needs to be processed to obtain point cloud data for the region of interest to be welded. This reduces subsequent computational effort and improves inspection efficiency and accuracy. The point cloud data for the region of interest to be welded is the point cloud data within the region obtained by registering, segmenting, and extracting the first point cloud data using point cloud processing software. This point cloud data for the region of interest to be welded contains the coordinate information for all points within the region.

[0064] Specifically, the first point cloud data is denoised and downsampled to obtain first target point cloud data, and the first maximum value set and the first minimum value set of the weld coordinates in the area to be welded in the three-dimensional coordinate direction are estimated. According to the first maximum value set and the first minimum value set, the coordinate range of the area to be welded in the three-dimensional coordinate axis direction is determined. The area formed by the coordinate range is the area of ​​interest to be welded. The point cloud data of the area to be welded is screened, and the point cloud data of the coordinate values ​​of the weld point cloud data in the three-dimensional coordinate direction within the area of ​​interest to be welded are extracted to obtain the point cloud data of the area of ​​interest to be welded.

[0065] Based on the above embodiment, as an optional embodiment, the step of determining the point cloud data of the area of ​​interest to be welded based on the first point cloud data and the area to be welded may further include the following steps:

[0066] Step 201: De-noising and downsampling the first point cloud data to obtain first target point cloud data.

[0067] Specifically, since the first point cloud data may contain some noise or outliers, it needs to be denoised. This denoising process can be performed using filtering algorithms, such as Gaussian filtering, median filtering, and bilateral filtering. These filtering algorithms can effectively remove noise and outliers, preserving valid information in the point cloud data.

[0068] Furthermore, since the first point cloud data typically contains a large number of points, it is necessary to downsample the denoised point cloud data to reduce the number and complexity of the point cloud data. Downsampling methods can include voxel grid downsampling, random sampling, distance-based sampling, etc. These methods can be optimized based on the distribution and density of the point cloud data to obtain downsampled first target point cloud data with a certain degree of accuracy.

[0069] Step 202: Estimate a first maximum value set and a first minimum value set of weld seam coordinates in the area to be welded in the three-dimensional coordinate direction.

[0070] Specifically, the point cloud data of the weld area is segmented, and the area where the weld is located is extracted from the point cloud data to obtain the weld point cloud data. The weld point cloud data is processed to obtain the coordinate values ​​of the weld point cloud data in the three-dimensional coordinate direction, namely the x-axis coordinate value, the y-axis coordinate value, and the z-axis coordinate value. In the embodiment of this application, the three-dimensional coordinate direction refers to three mutually perpendicular axes that describe the position or direction in space. In a three-dimensional coordinate system, three axes are used to represent the position or direction. These axes are the X-axis, the Y-axis, and the Z-axis, and each axis is perpendicular to the plane perpendicular to it.

[0071] Furthermore, statistical analysis is performed on the coordinate values ​​of the weld point cloud data in the x-axis, y-axis, and z-axis directions to obtain the first maximum value set in the x-axis, y-axis, and z-axis directions, as well as the first minimum value set in the x-axis, y-axis, and z-axis directions. Statistical methods such as the range method, quantile method, and standard deviation method can be used for calculation.

[0072] Step 203: Determine the point cloud data of the area of ​​interest to be welded based on the first maximum value set, the first minimum value set, and the first target point cloud data.

[0073] Specifically, the first target point cloud data is segmented and divided into a weld area and a non-weld area, the point cloud data of the weld area is processed, and the coordinate values ​​of the weld point cloud data in the three-dimensional coordinate direction, such as the z-axis coordinate value, are obtained. According to the first maximum value set and the first minimum value set, the coordinate range of the region of interest to be welded in the three-dimensional coordinate axis direction is determined, the point cloud data of the weld area is screened, and the point cloud data of the coordinate values ​​of the weld point cloud data in the three-dimensional coordinate direction within the region of interest to be welded are retained to obtain the point cloud data of the region of interest to be welded, that is, point cloud data with a certain precision and accuracy can be obtained for subsequent processing and analysis.

[0074] Step 30: Based on the second point cloud data and the welded area, determine the point cloud data of the welded area of ​​interest.

[0075] Because a 3D laser scanner can scan a large area and potentially overlap, the second point cloud data needs to be processed to obtain point cloud data for the welded region of interest. This reduces subsequent computational effort and improves inspection efficiency and accuracy. The point cloud data for the welded region of interest is the point cloud data within the area obtained by registering, segmenting, and extracting the second point cloud data using point cloud processing software. This point cloud data for the welded region of interest contains the coordinate information for all points within the area.

[0076] Specifically, the second point cloud data is denoised and downsampled to obtain second target point cloud data, and the second maximum value set and the second minimum value set of the weld coordinates in the welded area in the three-dimensional coordinate direction are estimated. According to the second maximum value set and the second minimum value set, the coordinate range of the welded area in the three-dimensional coordinate axis direction is determined. The area formed by the coordinate range is the welded area of ​​interest. The point cloud data of the welded area is screened, and the point cloud data of the coordinate values ​​of the weld point cloud data in the three-dimensional coordinate direction within the welded area of ​​interest are extracted to obtain the point cloud data of the welded area of ​​interest.

[0077] Based on the above embodiment, as an optional embodiment, the step of determining the point cloud data of the welded area of ​​interest based on the second point cloud data and the welded area may further include the following steps:

[0078] Step 301: De-noising and downsampling the second point cloud data to obtain second target point cloud data.

[0079] Step 302: Estimate a second maximum value set and a second minimum value set of weld seam coordinates in the welded area in the three-dimensional coordinate direction.

[0080] Step 303: Determine the point cloud data of the welded region of interest based on the second maximum value set, the second minimum value set, and the second target point cloud data.

[0081] Specifically, the implementation method of the above steps 301 to 303 can refer to the above steps 201 to 203. The determination of the point cloud data of the welded area of ​​interest is the same as that of the area of ​​interest to be welded, and will not be repeated here.

[0082] Step 40: Perform point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result.

[0083] Point cloud matching refers to the registration of two or more point cloud data sets to achieve alignment and fusion of the point cloud data. In the embodiment of the present application, the point cloud data of the area of ​​interest to be welded is matched with the point cloud data of the welded area of ​​interest. The point cloud data of the two areas are merged into a whole. By calculating the pose transformation matrix, the alignment and matching between the point clouds can be achieved, so that the welded area can be processed and analyzed later, improving the accuracy and efficiency of the welded area detection.

[0084] Specifically, the iterative closest point method is a method for registering and aligning two or more point cloud data. It continuously optimizes the registration error between the point cloud data through iteration until the error is minimized. The point cloud data of the welded area of ​​interest is used as the reference point cloud, and the point cloud data of the area of ​​interest to be welded is used as the point cloud to be registered. A point is selected in the point cloud to be registered, and the point closest to the point in the reference point cloud is found. The distance error between the corresponding point pairs between the point cloud to be registered and the reference point cloud is calculated to measure the registration error between the two point cloud data. The rigid body transformation matrix of the point cloud to be registered is optimized by minimizing the distance error, so that its position and posture relative to the reference point cloud are closer. The above steps are repeated until the distance error between the point cloud data reaches a preset threshold or the maximum number of iterations is reached. The iterative closest point algorithm is then used to calculate the pose transformation matrix, and the point cloud data of the area of ​​interest to be welded is transformed to align it with the point cloud data of the welded area of ​​interest. The pose transformation matrix is ​​used as the matching result.

[0085] Step 50: Extract the weld point cloud set based on the matching results.

[0086] Specifically, based on the pose transformation matrix in the matching results, each point in the welded region of interest is transformed through the pose transformation matrix to obtain its corresponding point on the region of interest to be welded. By sequentially traversing the point cloud data of the region of interest to be welded, that is, for any target point in the welded region of interest, the Euclidean distance between each point and the target point is calculated, and the point with the smallest distance is selected as the corresponding point. If the distance is less than or equal to the weld extraction threshold, the point cloud data of the welded region corresponding to the point is added to the weld point cloud set, thus obtaining a weld point cloud set. This can control the extraction progress and quantity of weld points, effectively improving the accuracy and efficiency of subsequent weld detection.

[0087] Step 60: Analyze the weld point cloud set based on the point cloud principal component analysis method to obtain the size of each weld.

[0088] The point cloud principal component analysis method is to project the point cloud data onto the principal component axis to obtain the variance and mean in each principal component direction, thereby obtaining the size information of the point cloud data in each direction.

[0089] Specifically, the weld point cloud set is converted into a point cloud matrix and a principal component analysis is performed. Each row of the point cloud matrix corresponds to a point, and each column corresponds to a dimension (e.g., X, Y, Z coordinates). The point cloud matrix can be subjected to principal component analysis to obtain the variance and mean in each principal component direction. The principal component direction corresponds to the main distribution direction of the point cloud data. Based on its direction and variance information, the size of each weld in the X, Y, and Z directions can be determined. For example, the standard deviation in each principal component direction can be calculated to obtain the size information of the weld in each direction. The size of the weld in the X, Y, and Z directions can correspond to the length, width, and depth of the weld, respectively.

[0090] Furthermore, after obtaining the dimensions of each weld, the dimensions of each weld are compared with preset standard weld size ranges. The preset standard weld size ranges may be manually set standard ranges for weld length, width, and depth. Welds whose dimensions do not meet the preset standard weld size ranges are determined as unqualified welds, while welds whose dimensions meet the preset standard weld size ranges are determined as qualified welds. This allows personnel to clearly determine whether the welds are compliant, thereby facilitating subsequent weld inspection and acceptance.

[0091] Welds can be further categorized by size to determine the number and proportion of welds within different size ranges. Statistics such as the average size and standard deviation of welds can also be calculated to provide a more comprehensive picture of weld size distribution.

[0092] Please refer to Figure 2, which is a schematic diagram of a 3D laser scanner for weld detection according to an embodiment of the present application. The following describes the implementation principles of the embodiment of the present application in conjunction with Figure 2. First, the 3D laser scanner is controlled to a pre-welding scanning position, and the 3D laser scanner's posture is adjusted so that the weld in the area to be welded is within the 3D laser scanner's measurement range. First point cloud data of the area to be welded before welding is acquired by the 3D laser scanner. The 3D laser scanner is controlled to move to a post-welding scanning position according to a preset movement path 3. The 3D laser scanner's posture is again adjusted so that the weld in the welded area is within the 3D laser scanner's measurement range, and second point cloud data of the welded area after welding is acquired. Based on the first point cloud data and the area to be welded, point cloud data of the area of ​​interest to be welded is determined. Based on the second point cloud data and the welded area, point cloud data of the welded area of ​​interest is determined. Point cloud matching is performed between the point cloud data of the welded area of ​​interest and the point cloud data of the welded area of ​​interest to obtain a matching result. A weld point cloud set is extracted based on the matching result, and the weld point cloud set is analyzed using point cloud principal component analysis to obtain the dimensions of each weld.

[0093] Please refer to FIG3 , which is a schematic diagram of a module of a weld size detection system based on point cloud matching provided in an embodiment of the present application. The weld size detection system based on point cloud matching may include: a point cloud data acquisition module 301, a region of interest acquisition module 302, a point cloud matching module 303, a weld point cloud set extraction module 304, and a weld size generation module 305, wherein:

[0094] The point cloud data acquisition module 301 is used to acquire first point cloud data of the area to be welded before welding acquired by a 3D laser scanner, and second point cloud data of the welded area after welding acquired by the 3D laser scanner;

[0095] The region of interest acquisition module 302 is configured to determine point cloud data of a region of interest to be welded based on the first point cloud data and the region to be welded; and to determine point cloud data of a region of interest to be welded based on the second point cloud data and the welded region.

[0096] A point cloud matching module 303 is used to perform point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result;

[0097] A weld point cloud set extraction module 304 is used to extract a weld point cloud set according to the matching result;

[0098] The weld size generating module 305 is configured to analyze the weld point cloud set based on a point cloud principal component analysis method to obtain the sizes of each weld.

[0099] It should be noted that the above embodiments provide systems that implement their functions using only the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0100] This application also discloses an electronic device. Referring to FIG4 , FIG4 is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 400 may include: at least one processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0101] The communication bus 402 is used to implement the connection and communication between these components.

[0102] The user interface 403 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 403 may also include a standard wired interface and a wireless interface.

[0103] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0104] Processor 401 may include one or more processing cores. Using various interfaces and circuits, processor 401 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in memory 405, as well as accesses data stored in memory 405, to perform various server functions and process data. Optionally, processor 401 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). Processor 401 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 401 and implemented as a separate chip.

[0105] Memory 405 may include random access memory (RAM) or read-only memory (ROM). Optionally, memory 405 may include non-transitory computer-readable storage medium. Memory 405 may be used to store instructions, programs, code, code sets, or instruction sets. Memory 405 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, sound playback function, image playback function, etc.), instructions for implementing each of the aforementioned method embodiments, and the data storage area may store data related to each of the aforementioned method embodiments. Memory 405 may also optionally be at least one storage device located remotely from the processor 401. Referring to Figure 4 , memory 405, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application for a weld size detection method based on point cloud matching.

[0106] In the electronic device 400 shown in FIG4 , the user interface 403 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 401 can be used to call an application program stored in the memory 405 for a weld size detection method based on point cloud matching. When executed by one or more processors 401, the electronic device 400 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited by the described order of actions, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0107] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0109] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0110] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0112] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0113] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. A weld size detection method based on point cloud matching, characterized in that: The method comprises: Acquire first point cloud data of the area to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of the welded area after welding collected by the three-dimensional laser scanner; Determine point cloud data of an area of ​​interest to be welded based on the first point cloud data and the area to be welded; Determine point cloud data of a welded area of ​​interest based on the second point cloud data and the welded area; Performing point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result; Extracting a weld point cloud set according to the matching result; The weld point cloud set is analyzed based on the point cloud principal component analysis method to obtain the size of each weld.

2. The weld size detection method based on point cloud matching according to claim 1 is characterized in that: Acquiring first point cloud data of the area to be welded before welding collected by a three-dimensional laser scanner, and second point cloud data of the welded area after welding collected by the three-dimensional laser scanner, including: Adjusting the posture of the three-dimensional laser scanner according to the weld in the area to be welded, so that the weld in the area to be welded is within the measurement range of the three-dimensional laser scanner; Acquire first point cloud data of the area to be welded collected by the three-dimensional laser scanner; Adjusting the posture of the three-dimensional laser scanner according to the weld in the welded area so that the weld in the welded area is within the measurement range of the three-dimensional laser scanner; Acquire second point cloud data of the welded area collected by the three-dimensional laser scanner.

3. The weld size detection method based on point cloud matching according to claim 1 is characterized in that: The step of determining the point cloud data of the area of ​​interest to be welded based on the first point cloud data and the area to be welded further comprises: De-noising and downsampling the first point cloud data to obtain first target point cloud data; estimating a first maximum value set and a first minimum value set of weld seam coordinates in the area to be welded in a three-dimensional coordinate direction; Based on the first maximum value set, the first minimum value set and the first target point cloud data, point cloud data of the area of ​​interest to be welded is determined.

4. The weld size detection method based on point cloud matching according to claim 1, characterized in that: The step of determining the point cloud data of the welded area of ​​interest based on the second point cloud data and the welded area includes: De-noising and downsampling the second point cloud data to obtain second target point cloud data; estimating a second maximum value set and a second minimum value set of weld seam coordinates in the welded area in the three-dimensional coordinate direction; Based on the second maximum value set, the second minimum value set and the second target point cloud data, point cloud data of the welded area of ​​interest is determined.

5. The weld size detection method based on point cloud matching according to claim 1, characterized in that: The step of performing point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result includes: Based on the iterative closest point method, point cloud matching is performed on the point cloud data of the region of interest to be welded and the point cloud data of the welded region of interest, and a pose transformation matrix is ​​calculated; The pose transformation matrix is ​​used as the matching result.

6. The weld size detection method based on point cloud matching according to claim 5 is characterized in that: The step of extracting a weld point cloud set according to the matching result comprises: Based on the posture transformation matrix in the matching result, the point cloud data of the welded region of interest is converted to the region of interest to be welded; For any target point in the welded region of interest: The point cloud data with the shortest Euclidean distance to the target point is determined in the point cloud data of the area of ​​interest to be welded, and the points corresponding to the point cloud data of the welded area whose shortest Euclidean distance is greater than the weld extraction threshold in the area of ​​interest to be welded are taken as weld points to obtain a weld point cloud set.

7. The weld size detection method based on point cloud matching according to claim 1 is characterized in that: After analyzing the weld point cloud set based on the point cloud principal component analysis method to obtain the size of each weld, the method includes: Comparing the size of each weld with a preset standard weld size range, the weld size including length, width and depth; Determine a weld whose size does not meet a preset standard weld size range as an unqualified weld; A weld whose size meets a preset standard weld size range is determined as a qualified weld.

8. A weld size detection system based on point cloud matching, characterized in that: The system comprises: A point cloud data acquisition module (301) is used to acquire first point cloud data of the area to be welded before welding acquired by a three-dimensional laser scanner, and second point cloud data of the welded area after welding acquired by the three-dimensional laser scanner; An area of ​​interest acquisition module (302) is used to determine the point cloud data of the area of ​​interest to be welded based on the first point cloud data and the area to be welded; and to determine the point cloud data of the welded area of ​​interest based on the second point cloud data and the welded area; A point cloud matching module (303) is used to perform point cloud matching on the point cloud data of the welding region of interest and the point cloud data of the welded region of interest to obtain a matching result; A weld point cloud set extraction module (304), used to extract a weld point cloud set according to the matching result; The weld size generation module (305) is used to analyze the weld point cloud set based on the point cloud principal component analysis method to obtain the sizes of each weld.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory and a transceiver, the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

Images