Improved ICP and kd tree-based maintainability component accurate registration method, system and equipment

Abstract

The invention discloses a maintainability component accurate registration method, system and equipment based on an improved ICP and kd tree, and belongs to the technical field of product maintainability tests.The method includes the steps that normal vector information of STL triangular meshes in a three-dimensional CAD model is fully utilized, and the nearest point between scene point cloud and the corresponding triangular meshes is calculated to obtain a final point; and taking the nearest points as target corresponding points for registration, and then performing efficient nearest neighbor search by using a k-dtree data structure to optimize key point selection in the registration process. By constructing a division tree of a multi-dimensional space, rapid space division and retrieval are realized. In the process, the Euclidean distance is used as a measurement standard, the registration key points are screened, and only the key points with the distances from the query points within a set threshold value are reserved, so that the registration efficiency is remarkably improved. The robustness of the method is verified through multiple groups of public data set experiments, and compared with an LM-ICP algorithm, a Point-to-plane ICP algorithm and a traditional ICP algorithm, the algorithm provided by the invention reduces the registration time by 30%.

Description

Technical Field

[0001] The invention relates to the technical field of product maintainability test, and in particular to a maintainability component accurate registration method, system and equipment based on improved ICP and kd tree. Background Art

[0002] Maintainability is an inherent quality attribute of a product, and maintainability engineering technology plays a vital role in improving product availability and reducing maintenance costs. With the increasing complexity of product structures and the continuous improvement of usage requirements, how to improve the maintainability level of products has attracted widespread attention from scholars. Especially for critical equipment and facilities, optimizing maintainability design can not only enhance the safety of maintenance operations, but also ensure the smooth completion of tasks. Therefore, in-depth research on the analysis, testing and evaluation methods for maintainability design schemes and prototypes plays an important role in improving product quality and ensuring product safety.

[0003] Traditional maintainability test methods usually rely on physical prototypes or full-size models, which means that maintainability assessments can often only be conducted after the overall product design is completed. This practice makes the discovery of maintenance defects relatively delayed, which not only prolongs the product development cycle, but also increases the difficulty of later modifications and optimizations. With the continuous development of digital prototype technology and augmented reality technology (AR), virtual maintenance technology has emerged. It relies on high-fidelity simulation and highly interactive virtual scenes to enable engineers to truly simulate and deeply explore the maintenance processes and characteristics of future products. This technology can conduct a detailed analysis and strict review of the maintainability of the product in the early stages of design by rehearsing the entire maintenance operation and repair process in virtual reality, thereby effectively revealing and correcting potential design defects in advance, so as to optimize maintenance efficiency and reduce costs.

[0004] Virtual-reality fusion maintainability test is a cutting-edge maintainability test strategy. Its basic concept is to make up for the shortcomings of traditional physical and virtual maintainability test modes in terms of economy and accuracy. By using augmented reality (AR) technology to achieve seamless integration of virtual and physical objects, an integrated virtual-reality fusion maintainability test environment is built and maintainability test operations are carried out. It can truly reflect the impact of maintenance scenarios on maintenance prototypes and maintenance processes. At the same time, it uses people's perception and interaction capabilities of virtual model objects to obtain more realistic and accurate maintainability test data. In view of the shortcomings of traditional augmented reality maintenance systems in terms of maintenance status perception and judgment, the research team of the Air Force Engineering University proposed a maintenance process identification strategy based on probabilistic neural networks, aiming to improve the intelligent perception and judgment capabilities in the maintenance process, thereby optimizing maintenance efficiency and accuracy. Yang Kangkang from Nanjing University of Aeronautics and Astronautics proposed to build an augmented assembly guidance system based on Vuforia based on the open source augmented reality SDK and an augmented assembly guidance system based on Kinect. Wu Fei from Zhengzhou University proposed a state-driven augmented reality intelligent maintenance system to guide maintenance technicians to complete the disassembly and assembly of workpieces. Jia Wenzhe from Nanjing University of Science and Technology proposed a rocket launcher maintenance assistance system based on augmented reality. Combining the characteristics of HoloLens glasses and Unity3D platform, he used plane markers and SLAM to realize the tracking and registration of the system.

[0005] In order to obtain detailed three-dimensional scenes and spatial objects of maintainability tests and realize the alignment of virtual scenes and physical spaces, point cloud registration has become an important key technology. On the one hand, due to the limitation of FOV and the interference of factors such as angle occlusion and uneven illumination in the acquisition method of RGBD cameras, it is necessary to scan the object under test multiple times to collect more complete point cloud data. However, the point cloud data collected each time is located in a different camera coordinate system, so point cloud registration technology must be applied to unify the measured point cloud into the same coordinate system through appropriate spatial transformation. On the other hand, the acquired point cloud needs to be aligned with the point cloud in the virtual space, and the two need to be registered. For the registration of rigid point clouds, the ICP algorithm is a classic method recognized by the industry. However, this method needs to rely on the initial positions of the model point cloud and the scene point cloud, and there is a problem of long point cloud registration time. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention aims to provide a method, system and device for accurate registration of maintainable parts based on improved ICP and kd tree. First, the normal vector information of the STL triangular mesh in the three-dimensional CAD model is fully utilized. By calculating the nearest point between the scene point cloud and the corresponding triangular mesh, these nearest points are used as the target corresponding points for registration. Then, the kd tree data structure is used for efficient nearest neighbor search to optimize the selection of key points in the registration process. By constructing a partition tree of multidimensional space, fast space partitioning and retrieval are achieved. In this process, the Euclidean distance is used as a metric to screen the key points for registration, and only the key points whose distance to the query point is within the set threshold are retained, thereby significantly improving the efficiency of registration.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] The method for accurate registration of maintainable parts based on improved ICP and kd tree includes the following steps:

[0009] S1: Obtaining scene point cloud of maintainable parts in the online stage And the model point cloud in the offline stage Preprocess the point cloud data;

[0010] S2: Use the normal vector information of the STL triangular mesh in the 3D CAD model and the kd-tree algorithm to determine the scene point cloud Midpoint Cloud i The corresponding point q i ;

[0011] S3: Based on matching point pairs (p i ,q i ), calculate the rotation matrix R and translation vector T, and update the scene point cloud P;

[0012] S4: Repeat steps S2 and S3, make convergence judgment based on the distance mean square error, obtain the optimized rotation matrix R and translation vector T, and achieve accurate alignment of the maintainable parts.

[0013] Furthermore, the specific operation of step S2 includes the following steps:

[0014] S201: Calculate the scene point cloud using the normal vector information of the STL triangular mesh in the 3D CAD model Midpoint Cloud i The closest points between the corresponding triangular meshes are used as the target corresponding points for registration;

[0015] S202: Using the Euclidean distance threshold method to remove scene point clouds and model point cloud Noise in

[0016] S203: Use the kd-tree tree to perform nearest neighbor search and determine the point cloud p from the target corresponding points i The corresponding point q i .

[0017] Furthermore, the specific operation of step S201 includes: Contains N x A triangular mesh q i , where q i ={c i0 , c i1 , c i2 |n i}, c i0 , c i1 , c i2 Represents the three vertices of the i-th triangle mesh, n i is the normal vector corresponding to the plane where the triangular mesh is located, and the scene point cloud The point cloud p i Traverse the search model point cloud All the triangular meshes in the adjacent point are obtained i .

[0018] Furthermore, the specific operation of step S203 includes the following steps:

[0019] S2031: Preliminary search: Through the binary structure of the kd tree, recursively search along the tree structure starting from the root node, and gradually narrow the search range according to the partition dimension and partition value of each node until the nearest neighboring point to the given point is found;

[0020] S2032: Backtracking search: after finding the approximate nearest neighbor point, backtracking search is performed along the search path;

[0021] S2033: Iterative search: If a closer data point is found, jump to the corresponding child node space for further search;

[0022] S2034: Termination condition: The search process will continue until the search path is empty, that is, no data point closer than the current nearest neighbor point can be found. At this time, the nearest neighbor point to the given point is output.

[0023] Furthermore, in step S3, the updated scene point cloud P is recorded as P, then

[0024] P`=p i *R+T.

[0025] Furthermore, the specific operation of step S4 includes the following steps:

[0026] S401: repeat step S2 and step S3 to iterate;

[0027] S402: Calculate the distance mean square error d after the scene point cloud P is updated m ,

[0028]

[0029] Where p′ i is the point cloud p i The updated pose, n is the total number of point clouds;

[0030] S403: Convergence judgment: judge Δd=|d m -d m-1 |Whether it is within the set threshold μ, where d m-1 is the distance mean square error before the scene point cloud P is updated; if Δd<μ, the updated rotation matrix R and translation vector T are obtained; if Δd>μ, return to step S2 and continue the random sampling and matching process to further optimize the registration result, and finally obtain the optimized rotation matrix R and translation vector T.

[0031] Furthermore, the present invention also includes a maintainability component precise registration system based on improved ICP and kd-tree, including a point cloud preprocessing module, a point cloud matching module, a rigid body registration module and a convergence judgment module;

[0032] The point cloud preprocessing module is used to process the scene point cloud and model point cloud Perform pre-processing;

[0033] The point cloud matching module is used to determine the scene point cloud Midpoint Cloud i The corresponding point q i ;

[0034] The rigid body registration module is used to calculate the rotation matrix R and translation vector T;

[0035] The convergence judgment module is used for convergence judgment;

[0036] The point cloud preprocessing module, point cloud matching module, rigid body registration module and convergence judgment module are implemented using the method described above.

[0037] Furthermore, the present invention also includes an electronic device, which includes at least one processor and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor can execute the method described above.

[0038] The beneficial effects of the present invention are:

[0039] The present invention proposes a point cloud precision registration method based on improved optimization of iterative closest point (ICP). First, the normal vector information of the STL triangular mesh of the 3D CAD model is used to find the closest point between the scene point cloud and the corresponding triangular mesh as the target corresponding point for registration, and the kd tree is introduced on the basis of the original ICP algorithm to quickly search for the closest point pair to reduce the number of iterations. Its robustness has been verified by experiments on multiple sets of public data sets. Compared with LM-ICP, Point-to-plane ICP and traditional ICP algorithms, the algorithm proposed in this paper reduces the registration time by 30%. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of the improved iterative closest point algorithm in the present invention.

[0041] Figure 2 This is a schematic diagram of the kd-tree data structure in the present invention.

[0042] Figure 3 This is a diagram showing the object registration effect of the Stanford data model in the second simulation experiment of the present invention.

[0043] Figure 4 This is the preprocessing of the real engine CAD model in the second simulation experiment of the present invention.

[0044] Figure 5 This is the flow chart of point cloud registration of virtual prototype in simulation experiment 2 of the present invention.

[0045] Figure 6 This is a comparison chart of the registration results of different registration methods in the second simulation experiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0047] Embodiment 1:

[0048] Embodiment 1 provides a method for accurately registering maintainable components based on improved ICP and kd-tree, as shown in the attached Figure 1 As shown, the specific steps include:

[0049] S1: Obtaining scene point cloud of maintainable parts in the online stage And the model point cloud in the offline stage Preprocess the point cloud data;

[0050] Specifically, the 3D CAD prototype model of the maintainable component is downsampled into the point cloud PCD file format. The 3D mesh model in PLY format stores the model's vertices, facets, normal vector textures and other geometric information to obtain the model point cloud of the maintainable component in the offline stage. Use depth cameras to obtain scene point clouds of maintainable parts in the online stage Then the scene point cloud and model point cloud Point cloud simplification is performed. It should be noted that the specific operation of this step is prior art and will not be described in detail in this application.

[0051] Further, S2: using the normal vector information of the STL triangular mesh in the 3D CAD model and the kd-tree algorithm, determine the point cloud with the scene Midpoint Cloud i The corresponding point q i ;

[0052] Specifically, S201: Calculate the scene point cloud using the normal vector information of the STL triangular mesh in the 3D CAD model Midpoint Cloud i The closest points between the corresponding triangular meshes are used as the target corresponding points for registration;

[0053] The present invention adopts the corresponding point search algorithm based on STL triangular mesh. Find the same as p i The closest point between corresponding triangular meshes. The STL model approximates the original CAD design through a large number of triangular facets, striving to achieve high-precision approximation in geometric form. Each triangular facet is defined by the three-dimensional coordinates of its three vertices and an external normal vector. Such a data structure not only describes the shape of the model, but also implicitly expresses the directional information of the model surface.

[0054] STL model point cloud based on CAD model Contains N x A triangular mesh q i , where q i ={c i0 , c i1 , c i2 |n i}, c i0 , c i1 , c i2 Represents the three vertices of the i-th triangle mesh, n i is the normal vector corresponding to the plane where the triangle mesh is located. The algorithm first searches Middle distance p i The nearest triangle mesh q i , and calculate q iUpper distance p i The nearest point t i as a corresponding point.

[0055] The most basic strategy is to analyze the scene point cloud Each point in the search model point cloud All the triangular meshes in the i However, the algorithm for calculating the shortest distance from a point to the H-angle grid is complex, and the traversal search efficiency is very low. The present invention adopts different strategies according to the complexity of the target CAD model. If the target CAD model is relatively simple, such as a cube, the STL model only contains 12 triangle meshes. When the number of triangle meshes is relatively large, the STL triangle mesh vertices of the target CAD model can be directly used as the target point cloud to search for p i The k nearest neighbor points of p are found, and the triangles where the k nearest neighbor points are located are taken as the distance from p i The nearest candidate H angle grid, select the nearest one as q i .

[0056] S202: Using the Euclidean distance threshold method to remove scene point clouds and model point cloud Noise in

[0057] The distance threshold method can be used as a constraint to remove noise points. Its operations include the following:

[0058] (1) The point cloud data should be uniform, so the distance between corresponding point pairs should not be too large, otherwise they will be regarded as noise points. i and q i If dist is too large, it is regarded as a noise point pair and is removed.

[0059] (2) Due to the characteristics of point cloud data itself, the boundary points of the point cloud often easily form multiple corresponding point pairs, which should be eliminated.

[0060] (3) If and To form a corresponding point set, and The spatial topological relationship of should be consistent. Consider two sets of corresponding points P 1 and Q 1 , and P 2 and Q 2 , if |dist(P 1 -P 2 )-dist(Q 1 -Q 2 )|≥ε, it is regarded as a noise point and is removed, otherwise it is retained.

[0061] S203: Nearest neighbor search: Calculate each p i to q i The Euclidean distance of all points in , and use the kd-tree data structure for efficient search. By traversing the kd-tree, find the distance p i The nearest point i as matching point pairs. This step ensures fast and accurate nearest neighbor matching.

[0062] Specifically, the kd-tree data structure is as follows Figure 2 Taking the tree construction process of a two-dimensional point set as an example, first sort all the points in the point set along the x-axis direction, find the midpoint A, and divide the point set into two subsets along the x-axis direction using point A as the dividing point. Next, sort the two subsets along the y-axis direction and continue to divide the subsets based on the midpoint, as shown in the attached figure. Figure 2 As shown in (a) in the figure. By looping through the x-axis and y-axis directions, all points are finally added to the tree structure. The tree construction result of the example point set is as follows: Figure 2 As shown in (b).

[0063] Given a point P in a point cloud dataset 3 , the process of using KD tree for nearest neighbor search is as follows:

[0064] (1) Preliminary search: Through the binary structure of the KD tree, recursively search along the tree structure starting from the root node. According to the partition dimension and partition value of each node, gradually narrow the search range until a node that matches the given point P is found. 3 Approximate nearest neighbor points.

[0065] (2) Backtracking search: Once the approximate nearest neighbor point is found, the algorithm will backtrack along the search path.

[0066] (3) Iterative search: If a closer data point is found, the algorithm will jump to the corresponding child node space for further search.

[0067] (4) Termination condition: The search process will continue until the search path is empty, that is, no data point closer than the current nearest neighbor can be found. At this time, the algorithm output is consistent with the given point P 3 The nearest neighbor.

[0068] Further, step S3: based on the matching point pair (p i ,q i ), calculate the rotation matrix R and translation vector T, and update the scene point cloud P;

[0069] Based on matching point pairs (p i ,q i), calculate the rotation matrix R and translation vector T. Then, use these parameters to update the scene point cloud P, denoted as P`, then

[0070] P`=p i *R+T

[0071] Further, step S4: repeating step S2 and step S3, performing convergence judgment according to the distance mean square error, obtaining the optimized rotation matrix R and translation vector T, and realizing accurate registration of the maintainable parts.

[0072] Specifically, S401: repeat step S2 and step S3 to iterate;

[0073] S402: Calculate the distance mean square error d after the scene point cloud P is updated m ,

[0074]

[0075] In the formula, p` i is the point cloud p i The updated pose, n is the total number of point clouds;

[0076] S403: Convergence judgment: judge Δd=|d m -d m-1 |Whether it is within the set threshold μ, where d m-1 is the distance mean square error before the scene point cloud P is updated; if Δd<μ, the updated rotation matrix R and translation vector T are obtained; if Δd>μ, return to step S2 and continue the random sampling and matching process to further optimize the registration result, and finally obtain the optimized rotation matrix R and translation vector T.

[0077] Simulation experiment:

[0078] The feasibility and robustness of the improved iterative closest point algorithm proposed in the present invention are verified by simulation experiments, which are conducted on a test platform with specific hardware configuration and software environment. The experimental environment is shown in Table 1 below.

[0079] In terms of data selection, this simulation experiment used the Dragon and Drillbit models in the Stanford University 3D point cloud database. The point cloud data obtained by multiple scans of these models by a 3D scanner provided rich experimental materials for this simulation experiment. By adjusting the number of key points, this simulation experiment verified the accuracy of the improved iterative closest point algorithm (ICP) under different conditions. In addition, in order to further verify the practicality of the algorithm, this simulation experiment also used real laboratory data - the engine model, and conducted a virtual-real fusion test. By comparing with different algorithms, this simulation experiment more comprehensively evaluated the performance of the algorithm proposed in this invention in practical applications.

[0080] Table 1 Experimental environment information

[0081]

[0082] (1) Experimental analysis compared with the original ICP algorithm

[0083] In order to highlight the advantages and reliability of the improved ICP algorithm proposed in this invention compared with the traditional ICP algorithm, this simulation experiment selected the Stanford University public data set for detailed experimental comparison. Specifically, Dragon and Drill were selected as experimental objects. The point cloud data of Drill and Dragon are both high-density point cloud data, with the number of data points reaching tens of thousands. This simulation experiment first uses a voxel filter for downsampling, uses the ISS algorithm to extract key points from the downsampled point cloud data, and then calculates the matching relationship between the corresponding points of the point cloud. The three-dimensional structure of the two models, the corresponding relationship of the point cloud, and the point cloud registration effect are shown in the attached figure. Figure 3 shown.

[0084] In order to deeply compare the performance of the algorithm proposed in the present invention with the traditional ICP algorithm, this simulation experiment selected two sets of data sets, Dragon and Drill, for experimental verification. In these experiments, different numbers of key points were extracted, and time and root mean square error (MSE) were used as the main evaluation criteria. In order to ensure the reliability and accuracy of the results, this simulation experiment conducted 20 sets of experimental comparisons for each set of data. The experimental results are shown in Table 2 and Table 3 below. By adjusting the extraction parameters of the key points, this simulation experiment obtained different amounts of point cloud data, and processed and analyzed these data. The experimental data clearly show that the algorithm proposed in the present invention has good performance in both running time and accuracy.

[0085] Table 2 Precise registration results of the Dragon model with different numbers of key points

[0086]

[0087] Table 3. Drill model precise registration results under different numbers of key points

[0088]

[0089] (2) Comparative experimental analysis with other algorithms

[0090] In order to fully demonstrate the advantages of the improved ICP algorithm proposed in the present invention over LM-ICP, Point-to-plane ICP and traditional ICP algorithms, a series of experiments were designed in this simulation experiment. These experiments were carried out under the same key point set and matching conditions to ensure fair and accurate comparison. The Stanford University public data set was selected, which included multiple different objects, to verify the reliability of the algorithm of the present invention. During the experiment, the operation was strictly carried out in accordance with the same experimental settings and parameter configurations. By comparing the performance of various algorithms under the same conditions, the advantages of the improved ICP algorithm proposed in the present invention in terms of accuracy, efficiency, etc. can be more clearly seen.

[0091] The experimental results are shown in Table 4 and Table 5. The experimental results record in detail the specific performance of various algorithms on different objects. By comparing and analyzing these data, it can be concluded that the algorithm proposed in the present invention has higher accuracy and stability when processing three-dimensional point cloud data.

[0092] Table 4 Experimental comparison of Dragon model objects

[0093]

[0094] Table 5 Drill model object experimental comparison

[0095]

[0096] (3) Analysis of real experimental data

[0097] In order to further verify the reliability of the algorithm in the present invention, this simulation experiment uses real engine CAD model data in the laboratory as the test object. The CAD model is first preprocessed, including voxel downsampling and noise reduction, and then the improved iterative closest point algorithm proposed in the present invention is used to align these preprocessed data.

[0098] Due to the huge size of the point cloud data of engine parts, preprocessing is crucial. Voxel downsampling and noise reduction techniques are implemented to improve data quality and computational efficiency. Figure 4 It is revealed that the initial pose difference between the pre-processed engine point cloud data and the CAD model is significant, and the two need to be accurately aligned through a registration algorithm.

[0099] In the experiment, the preprocessed engine CAD model was accurately matched and compared with the traditional iterative closest point (ICP) algorithm, LM-ICP algorithm and Point-to-plane ICP algorithm. Figure 5 The model matching process is described in detail, from the initial misaligned state to the final accurate matching achieved by this algorithm, and each step reflects the efficiency and accuracy of the algorithm. Figure 6 The difference in the registration results of the algorithms is intuitively demonstrated, and it is obvious that the algorithm of the present invention is more outstanding in detail processing and overall alignment. In order to quantitatively evaluate the performance of the algorithm, this simulation experiment also records the running time and registration accuracy of the algorithm, as shown in Table 6 below. The data shows that the algorithm proposed in the present invention reduces the running time by about 30% compared with the traditional ICP algorithm. In addition, Table 7 lists in detail the results obtained by solving the rigid body transformation matrix of the point cloud. This key step is directly related to the registration accuracy of the model and the final alignment effect. It can be seen from the data in the table that the algorithm in the present invention shows higher stability and accuracy when solving the rigid body transformation matrix.

[0100] Table 6 Real data experimental comparison

[0101]

[0102] Table 7 Point cloud rigid body transformation matrix

[0103]

[0104] Embodiment 2:

[0105] Embodiment 2 provides a maintainable component precise registration system based on improved ICP and kd-tree, which specifically includes a point cloud preprocessing module, a point cloud matching module, a rigid body registration module and a convergence judgment module;

[0106] The point cloud preprocessing module is used to process the scene point cloud and model point cloud Perform pre-processing;

[0107] The point cloud matching module is used to determine the scene point cloud Midpoint Cloud i The corresponding point q i ;

[0108] The rigid body registration module is used to calculate the rotation matrix R and translation vector T;

[0109] The convergence judgment module is used for convergence judgment;

[0110] It should be noted that the point cloud preprocessing module, the point cloud matching module, the rigid body registration module and the convergence judgment module are implemented by using the maintainable component precise registration method based on the improved ICP and kd tree described in the first embodiment.

[0111] Embodiment three:

[0112] Embodiment three provides an electronic device, comprising at least one processor and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor can execute the method for precise registration of maintainable parts based on improved ICP and kd tree described in embodiment one.

[0113] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for accurate registration of maintainable parts based on improved ICP and kd-tree, characterized in that: The following steps are involved: S1: Obtaining scene point cloud of maintainable parts in the online stage And the model point cloud in the offline stage Preprocess the point cloud data; S2: Use the normal vector information of the STL triangular mesh in the 3D CAD model and the kd-tree algorithm to determine the scene point cloud Midpoint Cloud i The corresponding point q i ; S3: Based on matching point pairs (p i ,q i ), calculate the rotation matrix R and translation vector T, and update the scene point cloud P; S4: Repeat steps S2 and S3, make convergence judgment based on the distance mean square error, obtain the optimized rotation matrix R and translation vector T, and achieve accurate alignment of the maintainable parts.

2. The method for accurate registration of maintainable parts based on improved ICP and kd-tree according to claim 1, characterized in that: The specific operation of step S2 includes the following steps: S201: Calculate the scene point cloud using the normal vector information of the STL triangular mesh in the 3D CAD model Midpoint Cloud i The closest points between the corresponding triangular meshes are used as the target corresponding points for registration; S202: Using the Euclidean distance threshold method to remove scene point clouds and model point cloud Noise in S203: Use the kd-tree tree to perform nearest neighbor search and determine the point cloud p from the target corresponding points i The corresponding point q i .

3. The method for accurate registration of maintainable parts based on improved ICP and kd-tree according to claim 2, characterized in that: The specific operation of step S201 includes: Contains N x A triangular mesh q i , where q i ={c i0 , c i1 , c i2 |n i }, c i0 , c i1 , c i2 Represents the three vertices of the i-th triangle mesh, n i is the normal vector corresponding to the plane where the triangular mesh is located, and the scene point cloud The point cloud p i Traverse the search model point cloud All the triangular meshes in the adjacent point are obtained i .

4. The method for accurate registration of maintainable parts based on improved ICP and kd-tree according to claim 3, characterized in that: The specific operation of step S203 includes the following steps: S2031: Preliminary search: Through the binary structure of the kd tree, recursively search along the tree structure starting from the root node, and gradually narrow the search range according to the partition dimension and partition value of each node until the nearest neighboring point to the given point is found; S2032: Backtracking search: after finding the approximate nearest neighbor point, backtracking search is performed along the search path; S2033: Iterative search: If a closer data point is found, jump to the corresponding child node space for further search; S2034: Termination condition: The search process will continue until the search path is empty, that is, no data point closer than the current nearest neighbor point can be found. At this time, the nearest neighbor point to the given point is output.

5. The method for accurate registration of maintainable parts based on improved ICP and kd-tree according to claim 4, characterized in that: In step S3, the updated scene point cloud P is recorded as P`, then P`=p i *R+T。 6. The method for accurate registration of maintainable parts based on improved ICP and kd-tree according to claim 5, characterized in that: The specific operation of step S4 includes the following steps: S401: repeat step S2 and step S3 to iterate; S402: Calculate the distance mean square error d after the scene point cloud P is updated m , Where p′ i is the point cloud p i The updated pose, n is the total number of point clouds; S403: Convergence judgment: judge Δd=|d m -d m-1 |Whether it is within the set threshold μ, where d m-1 is the distance mean square error before the scene point cloud P is updated; if Δd<μ, the updated rotation matrix R and translation vector T are obtained; if Δd>μ, return to step S2 and continue the random sampling and matching process to further optimize the registration result, and finally obtain the optimized rotation matrix R and translation vector T.

7. The maintainability component precise registration system based on improved ICP and kd-tree is characterized by: It includes point cloud preprocessing module, point cloud matching module, rigid body registration module and convergence judgment module; The point cloud preprocessing module is used to process the scene point cloud and model point cloud Perform pre-processing; The point cloud matching module is used to determine the point cloud with the scene Midpoint Cloud i The corresponding point q i ; The rigid body registration module is used to calculate the rotation matrix R and translation vector T; The convergence judgment module is used for convergence judgment; Among them, the point cloud preprocessing module, the point cloud matching module, the rigid body registration module and the convergence judgment module are implemented by the method described in any one of claims 1-6.

8. An electronic device, characterized in that: The electronic device includes at least one processor and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor so that the processor can execute the method described in any one of claims 1-6.

Images