Point cloud data management and Web rapid identification visualization method

Abstract

The invention provides a point cloud data management and Web rapid identification visualization method, and relates to the technical field of point cloud data processing. After point cloud similar clustering is carried out on the point cloud database, adaptive denoising processing is carried out through a similar clustering result, and a denoised point cloud set is established; establishing a scale space pyramid, performing calling matching on the scale space pyramid by using a similar clustering result, and reconstructing a position multi-scale model according to a calling matching result; performing feature extraction of the de-noising point cloud set through a position multi-scale model, and establishing a tunnel structure feature set; and performing tunnel visual fitting by using the tunnel structure feature set, and creating a Web visual model. The technical problem that in the prior art, due to the fact that the tunnel point cloud data size is large and noise and redundant information exist, the Web visualization quality is not high is solved, and the processing efficiency and the rendering performance precision of the tunnel point cloud data at the Web end are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of point cloud data processing, and in particular to a point cloud data management and Web rapid identification and visualization method. Background Art

[0002] As the scale and complexity of tunnel projects continue to increase, point cloud data, as high-precision three-dimensional spatial data, has become an important tool in tunnel structure detection, monitoring and analysis. Point cloud data obtained through laser scanning, lidar and other technologies can accurately reflect the geometric shape and structural characteristics of the tunnel.

[0003] Traditional point cloud data processing software is mostly run on a single machine, which has limitations in data sharing, collaborative work, and Web-based use. With the development of 5G and WebGL technology, 3D Web applications have become a development trend. However, the huge scale of tunnel point cloud data makes the loading and rendering of the Web side face performance bottlenecks. When processing millions or hundreds of millions of points, the traditional rendering mechanism often leads to slow loading speeds, affecting the user experience. Secondly, the computing power of the Web platform and the rendering performance of the browser are relatively weak, especially when rendering complex tunnel structures, there are often freezes or delays, affecting real-time interaction and viewing effects. In addition, the noise and redundant information in the point cloud data also make the visualization effect unsatisfactory. Low-quality point cloud data may cause the details of the tunnel structure to be inaccurately presented, and cannot meet the needs of modern tunnel engineering for efficient data processing and convenient visualization. Summary of the invention

[0004] The present application provides a method for point cloud data management and Web rapid identification and visualization, which solves the technical problems in the prior art of slow Web loading and rendering jams, and low visualization quality due to the huge amount of tunnel point cloud data and the presence of noise and redundant information in the data. It achieves the technical effect of significantly improving the processing efficiency and rendering performance accuracy of tunnel point cloud data on the Web, thereby enhancing the sharing and collaboration of tunnel point cloud data.

[0005] In view of the above problems, the present application provides a point cloud data management and Web rapid identification visualization method, the method comprising: establishing a point cloud database, the point cloud database being used to store tunnel point cloud data; after performing point cloud similarity clustering on the point cloud database, adaptive denoising processing is performed through the similarity clustering results to establish a denoised point cloud set; establishing a scale space pyramid, using the similarity clustering results to call and match the scale space pyramid, and reconstructing a position multi-scale model according to the call and matching results; performing feature extraction of the denoised point cloud set through the position multi-scale model to establish a tunnel structure feature set; using the tunnel structure feature set to perform tunnel visualization fitting and create a Web visualization model.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By performing point cloud similarity clustering on the tunnel point cloud data stored in the point cloud database, selecting a suitable denoising algorithm for adaptive denoising processing based on the similarity clustering results, and establishing a denoised point cloud set, noise and irrelevant information can be reduced, thereby improving the quality of the tunnel point cloud data. A scale space pyramid is established, and the scale space pyramid is called and matched using the similarity clustering results. A position multi-scale model is reconstructed based on the call matching results, so that data can be analyzed at different scale levels, ensuring that the point cloud data can effectively express the tunnel structure at different scales, and providing more comprehensive information for subsequent feature extraction and other operations. Through the position multi-scale model, feature extraction is performed on the denoised point cloud set, and a tunnel structure feature set is established to further refine the capture of tunnel structure features, which not only retains the geometric structure information of the tunnel, but also enhances the recognition ability of complex structural features. Based on the extracted tunnel structure feature set, visual fitting and modeling are performed, and finally a Web visualization model is formed, which converts complex tunnel point cloud data into intuitive graphical display, making it convenient for users to view and interact through the Web platform and understand the details of the tunnel structure, thereby improving the convenience and real-time performance of data display and interaction.

[0008] In summary, this application combines multiple links such as data storage, denoising, scale analysis, feature extraction and visual display to improve the processing efficiency and accuracy of tunnel point cloud data. The point cloud database provides structured storage support, and similarity clustering and denoising ensure the quality of the data. The matching of scale space pyramid and similarity clustering optimizes the performance of point cloud data at different scales, and the position multi-scale model enhances the accuracy of feature extraction. Finally, through the Web visualization model, the tunnel structure data can be presented intuitively, and efficient, accurate and easy-to-interactive data display is achieved, making the management, analysis and display process of tunnel point cloud data more efficient and accurate, providing strong support for the intelligent management of tunnel projects.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of a point cloud data management and Web rapid identification visualization method provided in an embodiment of the present application.

[0011] Figure 2A schematic diagram of a process for clustering all nodes in a point cloud image using initial clustering points in a point cloud data management and Web rapid identification visualization method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The embodiment of the present application provides a method for point cloud data management and Web rapid identification and visualization. After performing point cloud similarity clustering on the tunnel point cloud data, adaptive denoising is performed through the similarity clustering results, and then a scale space pyramid is established. The scale space pyramid is called and matched using the similarity clustering results, and a position multi-scale model is reconstructed. The feature extraction of the denoised point cloud set is performed through the position multi-scale model, and a tunnel structure feature set is established. The tunnel structure feature set is used to perform tunnel visualization fitting and create a Web visualization model. The embodiment of the present application solves the technical problems in the prior art that the Web end loads slowly and renders stuck, and the visualization quality is not high due to the huge amount of tunnel point cloud data and the presence of noise and redundant information in the data, and achieves the technical effect of significantly improving the processing efficiency and rendering performance accuracy of tunnel point cloud data on the Web end, thereby enhancing the sharing and synergy of tunnel point cloud data.

[0013] like Figure 1 As shown, the embodiment of the present application provides a point cloud data management and Web rapid identification visualization method, the method comprising:

[0014] Step S1: Establish a point cloud database, where the point cloud database is used to store tunnel point cloud data.

[0015] Specifically, tunnel point cloud data refers to data obtained through laser scanning and other technologies, which describes the coordinates of each point on the tunnel surface in three-dimensional space. For example, when a laser scanner is used to scan the tunnel wall, the coordinate data of a large number of discrete points is point cloud data. Point cloud database is a database system used to store and manage tunnel point cloud data.

[0016] Use a database management system (such as a relational database such as MySQL or PostgreSQL, or a non-relational database such as MongoDB that is specifically used to process 3D data) to create a point cloud database. Interactive 3D laser scanners or other 3D data acquisition equipment obtain the point cloud data of the tunnel and store the data in a point cloud database in a certain format (for example, according to the acquisition time, acquisition area, etc.). By establishing a point cloud database, the centralized storage of tunnel point cloud data is realized, which facilitates subsequent data management, query and analysis, and provides a data foundation for the entire point cloud data processing process.

[0017] Step S2: After performing point cloud similarity clustering on the point cloud database, adaptive denoising is performed based on the similarity clustering results to establish a denoised point cloud set.

[0018] Specifically, the tunnel point cloud data in the point cloud database is clustered by point cloud similarity, and point cloud data with similar features (such as spatial position, geometric shape, etc.) are classified into one category. For example, point clouds of adjacent and similarly shaped areas on the tunnel wall can be clustered into one category. Based on the similarity clustering results, isolated points or abnormal points that do not match the clustering results are identified, the noise characteristics of the point cloud data in each cluster are analyzed, and a suitable denoising algorithm is selected to remove these points as noise points to establish a denoised point cloud set. For example, the voxel grid method or spatial neighborhood search can be used to analyze the noise distribution, intensity and type in the point cloud data, and the isolated noise points can be cleaned up by directly removing the noise points, and the edge noise points can be processed by weighted denoising.

[0019] The quality of point cloud data can be significantly improved through similarity clustering and denoising. The denoised point cloud set reduces the interference of irrelevant data, improves the accuracy and reliability of the data, and makes subsequent analysis and visualization more accurate.

[0020] Step S3: Establish a scale space pyramid, use the similarity clustering result to perform call matching on the scale space pyramid, and reconstruct a position multi-scale model according to the call matching result.

[0021] Specifically, in point cloud processing, the scale space pyramid can represent point cloud data through different resolution levels, helping to process tunnel structure information at different levels of detail. The position multi-scale model is a multi-scale model constructed on the basis of the scale space pyramid and combined with the spatial position information of the point cloud. This model can reflect the changes in tunnel structure at different scales. The point cloud database is analyzed for node distribution to determine the distribution of point cloud data in space, so as to determine parameters such as the limit scale and distribution coefficient, and construct a scale space pyramid. The point cloud data is matched with different scales of the scale space pyramid according to similar clustering results. If a certain type of point cloud data in the clustering result corresponds to a certain scale range in the scale space pyramid in space, a matching relationship between the point cloud data and the scale space pyramid is established based on this correspondence to generate a position multi-scale model.

[0022] The application of scale-space pyramid and multi-scale models enables the analysis and visualization of tunnel point cloud data at different resolutions, and can accurately extract information about the tunnel structure at all levels, while maintaining details and improving processing efficiency.

[0023] Step S4: performing feature extraction of the noise point cloud cluster through the position multi-scale model to establish a tunnel structure feature set.

[0024] Specifically, the tunnel structure feature set is a set of features that can represent the tunnel structure (such as the outline of the tunnel, the shape of key parts, etc.) extracted after a series of processing of the tunnel point cloud data. For example, the circular cross-sectional shape of the tunnel, the shape features of the vault, etc. can all be included in this feature set. Based on the multi-scale model of position, feature extraction algorithms (such as shape descriptor algorithms, etc.) are used to extract features from the denoised point cloud set. For example, features such as the curvature of the tunnel wall and the cross-sectional shape of the tunnel are extracted, and these extracted features are organized into a tunnel structure feature set. Feature extraction can be used to extract the key structural information of the tunnel, which helps to deeply analyze and understand the tunnel structure.

[0025] Step S5: Perform tunnel visualization fitting using the tunnel structure feature set to create a Web visualization model.

[0026] Specifically, the Web visualization model is a tunnel visualization model that can be viewed and interacted with on a Web browser. The tunnel structure feature set is used to perform tunnel visualization fitting through WebGL and other technologies. For example, the three-dimensional shape of the tunnel is drawn according to the cross-sectional shape characteristics of the tunnel, and the layout of the model in space is determined according to the direction characteristics of the tunnel. These features are converted into a three-dimensional model that can be displayed on a Web browser to create a Web visualization model. The Web visualization model allows users to easily view the three-dimensional structure of the tunnel on a Web browser without installing special three-dimensional software, which improves the sharing and interactivity of data and facilitates collaborative work and decision-making among personnel involved in tunnel engineering.

[0027] Furthermore, in step S2 of the embodiment of the present application, point cloud similarity clustering is performed on the point cloud database, including:

[0028] Step S21: taking each point in the point cloud database as a node, calculating the similarity between nodes, and constructing a point cloud graph.

[0029] Step S22: Obtain the calibration segmentation result of the tunnel, use the calibration segmentation result to distribute initial clustering points in the point cloud map, use the initial clustering points to perform clustering search for all nodes in the point cloud map, and complete point cloud similarity clustering according to the clustering search results.

[0030] Specifically, when performing point cloud similarity clustering, each point in the point cloud database is first treated as a node, and the similarity between points is measured using methods such as Euclidean distance and cosine similarity, and the similarity between each node is calculated. A point cloud graph is constructed based on the similarity between nodes. The nodes in this graph represent the points in the point cloud, and the edges represent the similarity between the points. The point cloud graph provides the topological structure of the point cloud data, which provides an analytical basis for the clustering of point cloud data.

[0031] The calibration segmentation result is the result of calibrating and segmenting the point cloud data using the geometric features (such as shape and size), geological features, construction features, etc. of the tunnel, and is used to determine the initial cluster point distribution in the point cloud map. The initial cluster point refers to the point pre-selected in the clustering process to start the clustering algorithm. Perform a preliminary segmentation of the tunnel point cloud data according to the tunnel characteristics to obtain the calibration segmentation result. Based on the calibration segmentation result, determine the location of the initial cluster point in the point cloud map. These initial cluster points are usually selected in the prominent area or boundary of the point cloud data. With the initial cluster point as the center, perform a cluster search of all nodes in the point cloud map to find points similar to the initial cluster point. Based on the cluster search results, similar points are classified into the same category to complete the point cloud similarity clustering.

[0032] By calibrating the segmentation results, the location of the initial clustering points can be determined more accurately, thereby guiding the clustering algorithm to more effectively identify and group similar point cloud data, providing a more accurate data set for subsequent denoising and feature extraction, and improving the accuracy and efficiency of clustering.

[0033] Further, such as Figure 2 As shown, in step S22 of the embodiment of the present application, the initial clustering points are used to perform clustering search of all nodes in the point cloud graph, including:

[0034] Step S22-21: Establishing a clustering fitness function, wherein the clustering fitness function is a function for performing clustering fitness calculation.

[0035] Step S22-22: After taking the initial cluster point as the cluster center, the cluster fitness function is used to perform cluster fitness calculation within the preset search range of the cluster center, wherein the cluster fitness calculation includes distance calculation between the node and the cluster center, cluster size calculation corresponding to the cluster center, and similarity calculation.

[0036] Step S22-23: perform cluster expansion according to the cluster fitness calculation result and reconstruct the cluster cluster.

[0037] Step S22-24: Search and update the cluster center of the reconstructed cluster clusters to establish a reconstructed cluster center.

[0038] Step S22-25: Execute search iterations to complete clustering searches of all nodes in the point cloud graph.

[0039] Specifically, the clustering fitness function is a function for evaluating the quality of clustering. The function measures the effect of clustering based on clustering feature parameters such as the distance between the node and the cluster center, the size of the cluster, and the similarity between the nodes, and evaluates the similarity between a certain point and the cluster center and the degree of cohesion of the cluster. A clustering fitness function is predefined to evaluate the effect of each cluster in the subsequent clustering process. Exemplarily, this function can contain multiple sub-functions, each of which calculates the distance between the node and the cluster center, the size of the cluster, and the similarity between the nodes, and the clustering fitness function is constructed by weighted averaging of multiple sub-functions.

[0040] With the initial cluster point as the center, set a preset search range. This search range can be a fixed distance threshold or a dynamic range determined by the point cloud distribution of the current cluster center. Within the preset search range, the cluster fitness function is used to calculate the distance between each node and the cluster center, the size of the cluster, and the similarity between nodes.

[0041] According to the result of the clustering fitness function, the point cloud data within the cluster is gradually expanded. If the fitness value of some points is high, it means that these points are similar to the current cluster center and can be added to the cluster. By expanding the cluster within the preset search range, the cluster is reconstructed to form a new clustering result. Then, the cluster center of the reconstructed cluster is searched and updated to establish a reconstructed cluster center to ensure that the new cluster center can better represent the nodes in the cluster. Reorganize the cluster according to the reconstructed cluster center. Perform search iterations and optimize the cluster center through multiple iterations until the cluster no longer changes significantly or the allocation of all nodes no longer changes, then stop the iteration.

[0042] Through the above clustering process, the nodes in the point cloud data will be effectively divided into multiple clusters with similar structures, and each cluster can more accurately represent the structural features in the tunnel. The establishment and search iteration of the newly added cluster centers make the clustering process not only limited to the initial cluster points, but can dynamically adapt to the distribution changes of the unclustered points, further improving the accuracy and robustness of the clustering, further ensuring the accurate segmentation of the tunnel point cloud data, improving the integrity and efficiency of data processing, and providing more reliable data support for subsequent denoising, feature extraction and visual modeling.

[0043] Furthermore, steps S22-25 of the embodiment of the present application also include:

[0044] Step S22-251: Determine whether there is a cluster search stop event, and if there is a cluster search stop event, generate a new instruction.

[0045] Step S22-252: Perform distribution analysis on the non-clustered nodes according to the new instructions and establish a new cluster center.

[0046] Step S22-253: Continue searching iteratively according to the newly added cluster center.

[0047] Specifically, the cluster search stop event means that during the clustering process, the cluster centers of some clusters have stabilized, no significant points are assigned to the cluster, or the search range of the cluster has reached a set threshold.

[0048] After each cluster expansion, the change of the current cluster is judged to confirm whether the conditions for stopping the search have been met. Specifically, if the distribution of the center point of a cluster and the points within the cluster has stabilized, and no new points are clustered into the cluster, it means that the search for the cluster has been completed, the cluster has reached a stable state, and its clustering quality can no longer be improved by adding new nodes. At this time, the search for the current cluster can be stopped, the status of the current completed cluster is recorded, and new instructions are generated for the unclustered nodes to prepare for subsequent clustering operations. The new instructions are used to guide further clustering processing of other unclustered nodes to add new clusters.

[0049] Unclustered nodes refer to nodes that have not been assigned to any clusters during the clustering process. After generating new instructions, the distribution of unclustered points is analyzed. According to the spatial position, point cloud density, similarity and other characteristics of the unclustered nodes, the distribution characteristics of these points are determined to determine whether these unclustered nodes are sufficient to form one or more new clusters. One or more new cluster centers are selected based on the distribution analysis results. These new cluster centers are usually the center of gravity of the unclustered point cloud data or areas with higher density.

[0050] According to the newly added cluster center, continue to search for nodes similar to the center and perform cluster expansion operations. Compare these unclustered points with the new cluster center through the cluster fitness function and expand the new cluster cluster. After each cluster expansion, update the cluster center according to the position of the newly added point and recalculate the cluster fitness. Repeat the cluster search iterative process to complete the cluster search of all nodes in the point cloud.

[0051] The above steps can effectively process the unclustered points by introducing the cluster stop search event and the new instructions, avoiding missing some structural parts in the tunnel point cloud data, ensuring the integrity of the clustering process, and avoiding omissions or misclassification.

[0052] Furthermore, in step S22 of the embodiment of the present application, obtaining the calibration and segmentation result of the tunnel includes:

[0053] Step S22-11: extract geometric features of the tunnel and establish a first segmentation constraint, where the geometric features include shape and size features of the tunnel.

[0054] Step S22-12: extract geological features of the tunnel and establish a second segmentation constraint.

[0055] Step S22-13: Perform temporal extraction of the construction features of the tunnel and establish a third segmentation constraint.

[0056] Step S22 - 14 : Using the first segmentation constraint, the second segmentation constraint, and the third segmentation constraint to establish the calibrated segmentation result.

[0057] Specifically, in point cloud data, geometric features usually include structural information such as the shape, size, curvature, and flatness of the tunnel. These features help identify the geometric boundaries of the tunnel, the shape of the pipe, etc. The geometric features are extracted from the tunnel point cloud data, and the first segmentation constraint is established based on the extracted geometric features to guide how to segment the tunnel point cloud data into different areas. For example, different areas can be segmented according to features such as the diameter and curvature of the tunnel. Assuming that the diameter of the tunnel is stable within a certain interval, the points in the point cloud data can be preliminarily segmented according to these stable geometric features to distinguish between areas such as the wall, ground, and top of the tunnel.

[0058] Geological features refer to the rock type, soil properties, structural levels and other geological features of the tunnel. Analyze the geological information in the point cloud data to identify different geological structures and features. According to the extracted geological features, establish the second segmentation constraint to effectively segment the tunnel point cloud data according to different geological layers. For example, a certain section of the tunnel passes through different rock layers with different densities and hardness. By extracting the geological features in the tunnel point cloud data, the different characteristics of the hard rock layer and the soft soil layer are identified, and these areas are divided in the point cloud data.

[0059] During the construction process, the shape of the tunnel will change over time. By extracting time series data, we can get the characteristics of the tunnel at different construction stages. For example, some areas may be exposed rock surfaces after excavation, and some areas are parts with completed support structures. According to the different construction stages, the third segmentation constraint is established to segment the point cloud data into areas that match the construction stage, so that the changes of the point cloud data at different stages can be effectively distinguished.

[0060] The aforementioned geometric feature constraints, geological feature constraints, and construction feature constraints are combined to generate the final calibration segmentation result. Each point cloud data point will be assigned to the appropriate category according to the constraints of these three features. This segmentation method can not only reflect the geometric structure of the tunnel, but also distinguish different geological layers and construction stages, making the processing of tunnel point cloud data more scientific and reasonable, and better reflecting the actual structure and construction status of the tunnel.

[0061] Furthermore, in step S3 of the embodiment of the present application, a scale space pyramid is established, including:

[0062] Step S31: performing node distribution analysis on the point cloud database and configuring a limit scale, wherein the limit scale includes a minimum scale and a maximum scale.

[0063] Step S32: Acquire the precision constraint of point cloud data management, and establish the distribution coefficient according to the precision constraint.

[0064] Step S33: constructing a scale space pyramid through the distribution coefficient and the limit scale.

[0065] Specifically, the spatial distribution of each node in the point cloud data is analyzed to evaluate its density, sparsity and other characteristics. The distance statistics between points, such as the average distance and the standard deviation of the distance, can be calculated to evaluate the changes in the density of nodes in different areas. Through this analysis, we can understand which areas of the point cloud data have more concentrated points and which areas have more sparse points. According to the results of the node distribution analysis, the limit scale is configured. The limit scale is the upper and lower limits of the scale range considered in the multi-scale analysis process, including the minimum scale and the maximum scale. Among them, the minimum scale is the smallest scale in the processing process, representing the scale of the smallest details or local structures in the point cloud. The maximum scale is the largest scale in the processing process, representing the scale of the coarsest and most macroscopic structure in the point cloud.

[0066] The accuracy constraints of point cloud data management are pre-set by the user according to specific application requirements and data quality requirements. For example, in some high-precision measurement applications, the accuracy of point cloud data is required to reach the millimeter level; while in some relatively rough analysis, the accuracy requirement may be reduced to the centimeter level. According to the needs of the tunnel project, obtain the corresponding point cloud data accuracy requirements. Establish the distribution coefficient based on the accuracy constraint. The distribution coefficient is a parameter determined according to the accuracy constraint in the construction of the scale space pyramid, which determines the detail retention and distribution of the point cloud data at different scales. The distribution coefficient is inversely proportional to the accuracy constraint, that is, the higher the accuracy requirement, the smaller the distribution coefficient; conversely, the lower the accuracy requirement, the larger the distribution coefficient.

[0067] The scale space pyramid is constructed by determining the distribution coefficient and the limit scale. The scale space pyramid constructs multiple levels by processing the point cloud data at different scales, and each level corresponds to a different scale range. Through this hierarchical structure, the tunnel point cloud data can be analyzed at different levels to obtain feature information at different scales. The specific construction process includes: using the configuration of the distribution coefficient and the limit scale, resampling and processing the point cloud data at multiple scale levels. For example, the specific values ​​of different scale levels can be determined according to the proportional relationship between the scales, such as in an equal proportion or logarithmic proportion. Then, for each scale level, the corresponding filtering or sampling method can be used to process the point cloud data. The bottom layer of the pyramid corresponds to a smaller scale and retains more details, while the top layer corresponds to a larger scale and focuses on more macroscopic features. Each scale level uses different resampling strategies to reduce the number of points while retaining key structural features, so that a suitable point cloud representation can be obtained at each scale, and finally a complete scale space pyramid is constructed.

[0068] By establishing a scale space pyramid, the tunnel point cloud data can be effectively organized at different scale levels, which can not only retain the fine local structural features, but also obtain the macroscopic overall structural information. This multi-scale analysis method can improve the flexibility and efficiency of point cloud data processing, balance the details and integrity in the point cloud data processing process, and provide more detailed and comprehensive support for subsequent visualization.

[0069] Furthermore, in step S3 of the embodiment of the present application, the scale space pyramid is called and matched using the similar clustering result, and the multi-scale model of the position is reconstructed according to the call and matching result, including:

[0070] Step S34: obtaining the optimal matching scale between the scale space pyramid and the similar clustering result.

[0071] Step S35: taking the optimal matching scale as the central scale, and performing multi-scale adaptive reconstruction at the position of the scale space pyramid according to the similarity clustering result and the central scale.

[0072] Step S36: establishing a position multi-scale model according to the multi-scale adaptive reconstruction result and the central scale.

[0073] Specifically, the similarity between certain features at each scale in the scale space pyramid and the corresponding features in the similar clustering results is calculated, and the scale that best matches the similar clustering results in each scale level of the scale space pyramid is determined, that is, the optimal matching scale. For example, the Euclidean distance, Mahalanobis distance, etc. can be used to calculate the similarity between the density features, shape features, etc. of the point cloud at different scales and the relevant features of the clusters in the similar clustering results. By comparing the similarity values ​​at different scales, the scale corresponding to the maximum similarity is found, which is the optimal matching scale.

[0074] The optimal matching scale is used as the central scale. This central scale is the core of the subsequent multi-scale adaptive reconstruction. Using the optimal matching scale as the central scale can make the reconstruction result better reflect the characteristics of the point cloud data. Multi-scale adaptive reconstruction is performed according to the similar clustering results and the position of the central scale in the scale space pyramid, and the representation of point cloud data or cluster clusters at different scales in the scale space pyramid is adjusted. For example, at the scale around the central scale, the point cloud at the corresponding scale is adjusted according to the similar clustering results, the information of the cluster cluster is integrated into the representation of the point cloud, or the point cloud at different scales is resampled or filtered according to the boundaries and structures of the cluster clusters to achieve multi-scale adaptation.

[0075] A multi-scale location model is established based on the multi-scale adaptive reconstruction results and the central scale. This multi-scale location model will integrate various information in the multi-scale adaptive reconstruction process, including the adjusted point cloud data at different scales, cluster information, and related information of the central scale, to ensure that the point cloud data at each scale can accurately reflect its actual position and structural characteristics in the tunnel, thereby more comprehensively and accurately describing the location characteristics of the point cloud data at different scales.

[0076] By establishing a multi-scale location model, the tunnel point cloud data can be fully displayed at multiple scale levels, ensuring the accuracy of the fine structure and macroscopic morphology, so that the complex structure of the tunnel is fully and accurately represented.

[0077] Furthermore, the method described in the embodiment of the present application also includes:

[0078] Step S61: performing abnormal feature recognition on the tunnel structure feature set, and creating abnormal annotations according to the abnormal feature recognition results.

[0079] Step S62: Visually display the abnormal annotation through a Web visualization model.

[0080] Specifically, an anomaly detection algorithm (such as an anomaly detection algorithm based on statistical analysis, etc.) is used to identify abnormal features of the tunnel structure feature set. For example, if the curvature of the tunnel wall suddenly changes significantly and exceeds the normal range, it is determined to be an abnormal feature. Anomaly annotations are created based on the identified abnormal features, such as special symbols or colors on abnormal points or areas. These abnormal annotations are then integrated into the Web visualization model and displayed on the Web browser so that users can intuitively see the abnormal areas.

[0081] Through abnormal feature recognition and visual display, abnormal conditions in the tunnel structure can be discovered and displayed in a timely manner, making it convenient for engineering personnel to quickly locate and analyze problems, thereby improving the safety and maintenance efficiency of the tunnel.

[0082] In summary, the point cloud data management and Web rapid identification visualization method provided by the embodiment of the present application has the following technical effects:

[0083] The embodiment of the present application first stores and manages the tunnel point cloud data through a point cloud database to provide data support for subsequent processing and analysis. Then, through similarity clustering and adaptive denoising processing, the noise is effectively removed, the quality of the point cloud data is improved, and the foundation is laid for accurate analysis. On this basis, a scale space pyramid is constructed, and scale matching and multi-scale adaptive reconstruction are performed in combination with similarity clustering results, so that the tunnel structure at different scales can be fully displayed, ensuring the consistency and accuracy of the data at all levels. Finally, the location multi-scale model is used to extract the tunnel structure features, and a Web visualization model is created to achieve accurate fitting and efficient visualization of the tunnel point cloud data. Through this technical solution, not only the accuracy and efficiency of tunnel point cloud data processing are improved, but also the expressiveness and consistency of point cloud data at different scales are significantly enhanced, which provides strong support for data analysis, monitoring and visualization in tunnel engineering, and solves the shortcomings of the prior art in terms of rapid Web identification and large-scale data processing.

[0084] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A point cloud data management and Web rapid identification visualization method, characterized in that: The method comprises: Establishing a point cloud database, wherein the point cloud database is used to store tunnel point cloud data; After performing point cloud similarity clustering on the point cloud database, adaptive denoising is performed based on the similarity clustering results to establish a denoised point cloud set; Establishing a scale space pyramid, using the similar clustering results to perform call matching on the scale space pyramid, and reconstructing a position multi-scale model according to the call matching results; Perform feature extraction of de-noised point clusters through the position multi-scale model to establish a tunnel structure feature set; The tunnel structure feature set is used to perform tunnel visualization fitting and create a Web visualization model.

2. A point cloud data management and Web rapid identification visualization method as claimed in claim 1, characterized in that: The performing point cloud similarity clustering on the point cloud database comprises: Taking each point in the point cloud database as a node, calculating the similarity between nodes, and constructing a point cloud graph; The calibration segmentation result of the tunnel is obtained, initial clustering points are distributed in the point cloud map using the calibration segmentation result, all nodes in the point cloud map are clustered and searched using the initial clustering points, and point cloud similarity clustering is completed according to the clustering search results.

3. A point cloud data management and Web rapid identification visualization method as claimed in claim 2, characterized in that: The using the initial clustering points to perform clustering search on all nodes in the point cloud graph includes: Establishing a clustering fitness function, wherein the clustering fitness function is a function for performing clustering fitness calculation; After taking the initial cluster point as the cluster center, the cluster fitness calculation within the preset search range of the cluster center is performed through the cluster fitness function, and the cluster fitness calculation includes the distance calculation between the node and the cluster center, the cluster size calculation corresponding to the cluster center, and the similarity calculation; Cluster expansion is performed according to the cluster fitness calculation results to reconstruct the cluster clusters; Search and update the cluster center of the reconstructed cluster clusters to establish the reconstructed cluster center; Search iterations are performed to complete cluster searches of all nodes in the point cloud graph.

4. A point cloud data management and Web rapid identification visualization method as claimed in claim 3, characterized in that: The performing of the search iterations comprises: Determine whether there is a cluster search stop event, and if there is a cluster search stop event, generate a new instruction; Perform distribution analysis on the unclustered nodes according to the newly added instructions and establish new cluster centers; The search iteration is continued according to the newly added cluster center.

5. A point cloud data management and Web rapid identification visualization method as claimed in claim 2, characterized in that: The step of obtaining the calibration and segmentation result of the tunnel includes: Extracting geometric features of the tunnel and establishing the first segmentation constraint, the geometric features include the shape and size features of the tunnel; Extract geological features of the tunnel and establish the second segmentation constraint; Perform time series extraction of tunnel construction features and establish the third segmentation constraint; The calibrated segmentation result is established using the first segmentation constraint, the second segmentation constraint, and the third segmentation constraint.

6. A point cloud data management and Web rapid identification visualization method as claimed in claim 1, characterized in that: The step of establishing a scale space pyramid comprises: Performing node distribution analysis on the point cloud database and configuring a limit scale, wherein the limit scale includes a minimum scale and a maximum scale; Obtaining precision constraints for point cloud data management, and establishing distribution coefficients according to the precision constraints; A scale space pyramid is constructed by using the distribution coefficient and the limit scale.

7. A point cloud data management and Web rapid identification visualization method as claimed in claim 6, characterized in that: The using the similar clustering results to perform call matching on the scale space pyramid, and reconstructing the position multi-scale model according to the call matching results, includes: Obtaining an optimal matching scale between the scale space pyramid and the similar clustering result; Taking the optimal matching scale as the central scale, and performing multi-scale adaptive reconstruction at the position of the scale space pyramid according to the similar clustering result and the central scale; A position multi-scale model is established according to the multi-scale adaptive reconstruction result and the central scale.

8. The point cloud data management and Web rapid identification visualization method according to claim 1, characterized in that: The method further comprises: Performing abnormal feature recognition on the tunnel structure feature set, and creating abnormal annotations according to the abnormal feature recognition results; The anomaly annotation is visualized through a Web visualization model.

Images