Drawing method, system and equipment based on point cloud data and storage medium

Abstract

The invention discloses a point cloud data-based charting method, system and device, and a storage medium. The method comprises the steps of obtaining point cloud data of a region needing charting; carrying out extraction, segmentation and boundary extraction on ground points in the point cloud data to obtain a ground contour line; extracting a building from non-ground points in the point cloud data, carrying out multi-plane segmentation on the building to extract wall point cloud, carrying out plane projection on the wall point cloud to obtain contour points of the building, and carrying out fitting to obtain a building contour line; and combining the ground contour line and the building contour line to obtain a final topographic map. Contour line recognition of buildings and structures and loading of topographic map expression conformance of the buildings and structures are achieved, and the drawing efficiency of two-dimensional line drawing is improved.

Description

Technical Field

[0001] This invention belongs to the field of three-dimensional laser scanning mapping, and relates to a mapping method, system, device and storage medium based on point cloud data. Background Technology

[0002] Since its development, 3D laser scanning technology has become another important measurement technique due to its characteristics such as fast scanning speed, dense point coverage, and area acquisition. It has been applied in industries such as building monitoring, cultural relic protection, and 3D design.

[0003] In station surveying, conventional surveying methods include total stations, GNSS, and UAVs. Currently, with the development of station-based scanners and mobile SLAM technology, scanning mapping has also become an important method. When using a total station, due to obstructions from buildings and trees, the instrument needs to establish a large number of control points for later mapping, resulting in relatively low efficiency. GNSS technology eliminates the need for on-site control points, allowing for immediate data acquisition and measurement. However, obstructions from buildings and trees within the station can lead to insufficient local satellite signals, affecting coordinate calculations and efficiency. UAVs can create 3D models and generate maps by taking photos of the station and establishing control points. However, for safety reasons, oil and gas stations often have no-fly zones or place jammers, thus impacting UAV mapping. 3D scanning mapping continuously acquires station scene data, which is then manually or automatically processed by software. The processed data can be displayed in 3D or 2D wireframe format, making it particularly suitable for older stations undergoing expansion or renovation.

[0004] When using point cloud data obtained from 3D scanning measurements to create 2D wireframe diagrams, the data is typically imported into CAD software like ZW3D or other drafting software. By orthographically projecting the point cloud data, a 2D outline image of the station can be displayed. Drafters can then interactively collect the outlines of buildings and structures within the station based on this image, thus creating a 2D line drawing of the station. However, in practical applications, operators need to draw wireframes from the projected image and then use these wireframes to draw features such as walls, buildings, large tanks, and roads. When there are numerous features, this process severely impacts the efficiency of creating 2D wireframe diagrams. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a mapping method, system, device and storage medium based on point cloud data, so as to realize the outline recognition of buildings and structures, the loading of topographic map symbols of buildings and structures, and improve the mapping efficiency of two-dimensional line drawing.

[0006] To achieve the above objectives, the present invention employs the following technical solution: A mapping method based on point cloud data includes the following steps: Obtain point cloud data for the area to be mapped; Ground points in point cloud data are extracted, segmented, and their boundaries are extracted to obtain ground contour lines; Buildings are extracted from non-ground points in point cloud data. Wall point clouds are extracted by multi-plane segmentation of buildings. The outline points of buildings are obtained by planar projection of the wall point clouds and then fitted to obtain the outline of buildings. The final topographic map is obtained by merging the ground outline and the building outline.

[0007] Preferably, after acquiring the point cloud data of the area to be mapped, a statistical analysis is performed on the neighborhood of each point to calculate its average distance to all neighboring points. Points whose average distance is outside the standard range are removed from the data.

[0008] Preferably, the ground point extraction process is as follows: potential ground seed points are obtained using morphological methods, accurate ground seed points are obtained from the potential ground seed points, a TIN-based model is constructed using the accurate ground seed points and the TIN is iteratively encrypted to extract ground points, and finally the ground points are normalized.

[0009] Preferably, ground point segmentation specifically involves segmenting ground points into vegetation point clouds and road point clouds. The boundary extraction process is as follows: perform planar projection on the road point cloud and vegetation point cloud respectively, extract the boundary and draw lines. Take any two points p1 and p2 in the point set S, and draw a circle with radius α through these two points. If there are no other points in the circle, then p1p2 is the boundary line, until all points are calculated.

[0010] Preferably, the process of extracting buildings from non-ground points is as follows: non-ground point clouds are obtained by segmenting ground points, and two parameters, neighborhood radius and minimum number of neighborhood points, are set to represent the density of the point cloud. The point that can reach the minimum number of points within the neighborhood radius is set as the core point. Clusters are continuously expanded from the core point to achieve clustering of clusters of arbitrary shapes, thereby extracting buildings.

[0011] Preferably, the process of extracting wall point cloud through multi-plane segmentation is as follows: the building point cloud C0 is segmented into multiple planes using the random sampling consensus algorithm, and then an angle threshold is set to extract the wall information of the building.

[0012] Preferably, the extracted building wall point cloud is projected onto a plane to obtain the building's outline points. The outline points are then simplified using feature preservation. Finally, model-based outline fitting is performed. The random sample consensus algorithm is used to calculate the model parameters for each sample set. The distance from each point to the model is then counted. Points with a distance less than the threshold are considered as inliers by setting an inlier threshold. After a large number of samples, the model with the most inliers is selected as the extraction result, and its inliers are the segmentation result corresponding to the extraction model. This process completes one segmentation step. The model is continuously segmented from the remaining point set by iteratively executing RANSAC to achieve the segmentation of all outline points. Finally, outline fitting is performed based on the model parameters, and lines are drawn to obtain the final building outline.

[0013] A mapping system based on point cloud data, comprising: The point cloud data acquisition module is used to acquire point cloud data of the area to be mapped. The ground point processing module is used to extract, segment, and extract boundaries of ground points in point cloud data to obtain ground contour lines; The non-ground point processing module is used to extract buildings from non-ground points in point cloud data, extract wall point clouds by multi-plane segmentation of buildings, obtain the outline points of buildings by planar projection of wall point clouds, and fit them to obtain the outline of buildings. The topographic map generation module is used to merge ground outlines and building outlines to obtain the final topographic map.

[0014] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the mapping method based on point cloud data.

[0015] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the mapping method based on point cloud data.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This invention, after acquiring point cloud data of a station using 3D laser scanning technology, automatically identifies the projected point cloud image, enabling automatic recognition of building outlines, loading of topographical map representations of buildings, automatic extraction and drawing of ground structures, minimizing manual intervention, and ensuring accurate drawing of ground structures. The software-defined outlines of ground structures allow for accurate extraction of wireframes, further reducing manual intervention. This improves the efficiency of 2D line drawing. Attached Figure Description

[0017] Figure 1This is a flowchart of the mapping method based on point cloud data of the present invention; Figure 2 This is a flowchart of the ground point extraction process of the present invention; Figure 3 This is a schematic diagram of the TIN model construction of the present invention; Figure 4 This is a flowchart of the ground point segmentation process of the present invention; Figure 5 This is a flowchart of the contour line fitting process of the present invention. Detailed Implementation

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0019] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terms “installation,” “connection,” and “linkage” should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection; a mechanical connection, an electrical connection, or a connection that allows communication; a direct connection or an indirect connection via an intermediate medium; or a connection within two elements or an interaction between two elements. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art will understand the specific meaning of the above terms in this invention according to the specific circumstances. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention.

[0021] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0022] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0023] The mapping method based on point cloud data described in this invention includes the following steps: ① Import the raw point cloud data.

[0024] ② Statistical filtering of point cloud data.

[0025] ③ Classify ground points in point cloud data.

[0026] ④ For ground point clouds, perform point cloud segmentation, vegetation and road point cloud extraction, planar projection, boundary extraction, and outline drawing.

[0027] ⑤ For non-ground point clouds, first perform point cloud clustering, then extract building point clouds, perform multi-plane segmentation, extract wall point clouds, project, simplify, model fit, and draw contour lines.

[0028] ⑥ Merge the outlines from steps 4 and 5.

[0029] ⑦ Import the outline from step 6 into CASS3D, draw a 2D line drawing, and assign attributes according to CASS legends to complete the output of engineering drawings.

[0030] The above process can be summarized as follows: First, point cloud data preprocessing is performed, and statistical filtering methods are used to filter outout points. Second, to reduce the complexity of ground feature information extraction, the point cloud is divided into ground points and non-ground points based on irregular triangular meshes. For ground point clouds, a region-growing-based point cloud segmentation method is used, and the similarity between point clouds is judged based on the angle between the normals of each point cloud to distinguish vegetation and road surfaces. Then, the three-dimensional point cloud space of vegetation and roads is projected onto a two-dimensional plane (xy plane), and boundary contour points are extracted and contour lines are drawn for each. For non-ground point clouds, due to the large number of building point clouds, density-based point cloud clustering is used, and a quantity threshold is set to extract building point clouds. The random sampling consistency method is used to perform multi-plane segmentation of building point clouds, retaining the three-dimensional information of the facade from each plane, obtaining the horizontal and vertical heights, identifying walls through analysis, projecting the wall point clouds onto the plane, simplifying the contour points, and retaining the feature points (including endpoints and corner points). For each building outline point, a outline is fitted and a line is drawn based on the model parameters to obtain the final building outline. Finally, the various outlines are merged and a graph is generated.

[0031] like Figure 1 As shown, the specific process is as follows: Step 1: Obtain point cloud data for the area to be mapped.

[0032] Step 2: Remove outliers using statistical filters. Perform a statistical analysis on the neighborhood of each point to calculate its average distance to all neighboring points. Assuming the result is a Gaussian distribution whose shape is determined by the mean and standard deviation, points whose average distance is outside the standard range (defined by the global distance mean and variance) can be defined as outliers and removed from the data.

[0033] Step 3, as follows Figure 2 As shown, ground point extraction.

[0034] (1) Use morphological methods to obtain potential ground seed points.

[0035] The original point cloud data is rasterized by taking the largest building size as the grid size. The lowest point in each grid is selected and added to the point set P to obtain the raster data P-grid. Morphological dilation, erosion and opening operations are performed on P-grid to obtain the rough ground. The height difference between the points in the point set P and the rough ground is calculated. Points less than 0.5m are potential ground seed points and added to the point set G0.

[0036] (2) Obtain accurate ground seed points.

[0037] For each point Pi in G0 and its k nearest neighbors, a kd-tree search is used in 3D space to obtain a locally fitted plane Fa using the eigenvalue method. The eigenvector corresponding to the smallest eigenvalue is the normal vector of the fitted plane. By parallelly shifting Fa to pass through Pi, a new plane Fb is obtained.

[0038] Add parameter r, which is calculated using formula (1) with k nearest neighbor points and plane Fb.

[0039] , (1) in Let Pi be the distance from Fb.

[0040] If r is greater than the threshold, point Pi is very likely to become a non-ground point, and it is removed from G0. The remaining points in G (the filtered seed points) are added to the ground seed point G1.

[0041] (3) Construct a TIN-based model and iteratively encrypt TIN to extract ground points.

[0042] like Figure 3 As shown, a sparse TIN is generated using ground seed points in G1 to construct the initial TIN.

[0043] Iterative encryption process: Traverse all ground feature points Pn (n=1, 2, 3, ...) to be classified, calculate the distance d from each point to the triangle in which its projection lies, and the angles between the point and the three vertices of the triangle and the triangle plane. Compare the calculated values ​​with the iterative distance D and the iterative angle α, respectively. If they are less than the corresponding threshold, the point is classified as a ground point and added to the triangulation network. Repeat this process until all ground points are classified.

[0044] (4) Ground point normalization processing.

[0045] In the subsequent classification process, normalization is required to remove the influence of terrain undulation on the elevation values ​​of ground features.

[0046] The specific method is as follows: Traverse the point cloud data to find ground features.

[0047] Subtract the elevation value of the nearest ground point from the elevation value Z of each feature point.

[0048] Set the elevation values ​​of all ground points to 0.

[0049] Elevation values ​​Z of non-ground points after normalization 终 It is calculated using formula (2).

[0050] Z 终 =Z-Z0,(2) Where Z is the original elevation, and Z0 is the elevation difference between Z and the nearest ground point.

[0051] Step 4, ground point segmentation.

[0052] like Figure 4 As shown, for the ground point cloud G, we need to segment it into vegetation point cloud and road point cloud. We select a road seed point pi from the point set G, construct its neighborhood relationship using a kd-tree, estimate its surface normal vector using principal component analysis, and calculate the angle between the surface normal vectors of point pi and its neighboring points. Vegetation areas are flatter than road areas, so their normal vector angles are larger. Therefore, we set an appropriate threshold based on the normal vector angle; points with normal vector angles less than the threshold are considered road points and added to the current seed region. We iterate through all neighboring points until the current region stops growing. For points not added, we select a new vegetation seed point and repeat the above operations to complete the segmentation of vegetation and roads.

[0053] Step 5, boundary extraction.

[0054] The exported road point cloud and vegetation point cloud need to be projected onto a plane separately, and then the boundaries are extracted and drawn. The idea is to take any two points p1 and p2 in the point set S, and draw a circle with radius α through these two points. If there are no other points inside the circle, then p1p2 can be considered as the boundary line. The specific operation process is as follows: (1) Establish an irregular triangular network based on the point set S.

[0055] (2) If the length of a side of a triangle is greater than 2α, then delete the triangle.

[0056] (3) Judge each edge of the triangular network again: if the circle passing through the two outer points and having a radius of α contains other points, then delete the triangle.

[0057] (4) Find the edge of the remaining triangular mesh, which is the edge line of the point set S.

[0058] Step 6: Extract buildings from non-ground points.

[0059] A non-ground point cloud J is obtained by segmenting ground points. Combining this with the characteristics of large quantity and strong structure in building point clouds, a density-based point cloud clustering algorithm is constructed. The algorithm sets two parameters: neighborhood radius and minimum number of points in the neighborhood, to represent the density of the point cloud. Points with the minimum number of points within the defined neighborhood radius are designated as core points. Clusters are continuously expanded from these core points, enabling clustering of clusters of arbitrary shapes. A threshold is set to segment the clustered point clouds; clusters with more points than the threshold are classified as building point clouds, while those with fewer points are classified as non-building point clouds.

[0060] The specific operating procedure is as follows: (1) For all points J1...Ji in the point set J, find all core points according to the following process. First, find the neighborhood points of sample point Ji by means of distance metric, and then add the sample points in the neighborhood that satisfy the condition that the number is greater than or equal to the minimum number in the neighborhood to the core point set.

[0061] (2) If the core point set is empty, the algorithm ends; otherwise, continue to the next step.

[0062] (3) In the set of core points, randomly select a core point O, and find the other core points of the cluster through the neighborhood radius parameter. Let C = C1, C2, ..., Cn.

[0063] (4) Repeat operation (3) until all core points are classified.

[0064] (5) The final output divides the non-ground point cloud into C=C1,C2,...,Cn.

[0065] (6) Set the quantity threshold to extract the building point cloud C0.

[0066] Step 7: Extract wall point cloud by multi-plane segmentation.

[0067] The random sample consensus algorithm (RANSAC) is used to perform multi-plane segmentation on the building point cloud C0. Then, an angle threshold is set to extract the building's facade information (i.e., wall information).

[0068] The specific process is as follows: (1) First, use the RANSAC algorithm to perform single-plane segmentation of the building and mark the local points.

[0069] (2) Use the RANSAC algorithm again to perform single-plane segmentation on the outliers.

[0070] (3) Repeat the above process until the number of outliers is less than a certain proportion of the total number of points or the number of segmented planes is greater than a certain threshold, then stop segmenting. At this point, multiple planes have been segmented.

[0071] (4) Remove non-facades from each plane. That is, if the angle between the normal vector of a plane and the Z-axis is greater than the set threshold, it is a non-facade and should be removed.

[0072] (5) In order to accurately identify the wall and non-wall surfaces in the facade, it is necessary to perform Euclidean clustering on the points in the facade. By limiting the minimum number of point clouds contained in the cluster and analyzing the width of the cluster in the horizontal direction and the height in the vertical direction, the wall and non-wall surfaces can be identified.

[0073] Step 8, contour fitting based on the model.

[0074] like Figure 5 As shown, the building facade point cloud extracted in step 7 is projected onto a plane to obtain the building's outline points. Point cloud simplification based on feature preservation (inflection points, endpoints, corner points) is performed on the outline points. Finally, model-based outline fitting is used, employing the Random Sample Consensus Algorithm (RANSAC). The model parameters (lines, circles, polygons, etc.) for each sample set are calculated, and the distance from each point to the model is counted. Points with a distance less than the threshold are considered interior points. After a large round of sampling, the model with the most interior points is selected as the extraction result, and its interior points represent the segmentation result corresponding to the extracted model. This process completes one segmentation cycle. RANSAC is repeatedly executed to continuously segment the model from the remaining point sets, achieving segmentation of all outline points. Finally, outline fitting is performed based on the model parameters, and lines are drawn to obtain the final building outline.

[0075] To address the issue of data redundancy after projection, feature-preserving point cloud simplification is needed to reduce data volume and improve efficiency without destroying the original features.

[0076] Step 9: Topographic map creation.

[0077] Using third-party software, the outlines of vegetation, roads, and buildings are merged and mapped, and then regularized to obtain the final topographic map.

[0078] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not omitted in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0079] In another embodiment of the present invention, a mapping system based on point cloud data is provided. This mapping system can be used to implement the above-mentioned mapping method based on point cloud data. Specifically, the mapping system based on point cloud data includes a point cloud data acquisition module, a ground point processing module, a non-ground point processing module, and a topographic map generation module.

[0080] The point cloud data acquisition module is used to acquire point cloud data for the area to be mapped.

[0081] The ground point processing module is used to extract, segment, and extract boundaries of ground points in point cloud data to obtain ground contour lines.

[0082] The non-ground point processing module is used to extract buildings from non-ground points in point cloud data, extract wall point clouds by multi-plane segmentation of buildings, obtain the outline points of buildings by planar projection of wall point clouds, and fit them to obtain the outline of buildings.

[0083] The topographic map generation module is used to merge ground outlines and building outlines to obtain the final topographic map.

[0084] In another embodiment of the present invention, a terminal device is provided, the terminal device including a processor and a memory, the memory being used to store a computer program, the computer program including program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to realize the corresponding method flow or corresponding function. The processor described in this embodiment of the invention can be used for the operation of a mapping method based on point cloud data, including: acquiring point cloud data of the area to be mapped; extracting, segmenting, and extracting boundaries of ground points in the point cloud data to obtain ground contour lines; extracting buildings from non-ground points in the point cloud data, extracting wall point clouds from multi-plane segmentation of buildings, obtaining the contour points of buildings by planar projection of the wall point clouds, and fitting them to obtain building contour lines; merging the ground contour lines and building contour lines to obtain the final topographic map.

[0085] In another embodiment, the present invention also provides a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understood that the computer-readable storage medium here may include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor, which may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here may be high-speed RAM or non-volatile memory, such as at least one disk storage device.

[0086] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the mapping method based on point cloud data in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: acquiring point cloud data of the area to be mapped; extracting, segmenting and extracting boundaries of ground points in the point cloud data to obtain ground contour lines; extracting buildings from non-ground points in the point cloud data, extracting wall point clouds from multi-plane segmentation of buildings, obtaining building contour points by planar projection of wall point clouds, and fitting them to obtain building contour lines; merging ground contour lines and building contour lines to obtain the final topographic map.

[0087] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0092] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this patent should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the applicant has not considered that subject matter as part of the disclosed inventive subject matter.

Claims

1. A mapping method based on point cloud data, characterized in that, The process includes the following: Obtain point cloud data for the area to be mapped; Ground points in point cloud data are extracted, segmented, and their boundaries are extracted to obtain ground contour lines; Buildings are extracted from non-ground points in point cloud data. Wall point clouds are extracted by multi-plane segmentation of buildings. The outline points of buildings are obtained by planar projection of the wall point clouds and then fitted to obtain the outline of buildings. The final topographic map is obtained by merging the ground outline and the building outline.

2. The mapping method based on point cloud data according to claim 1, characterized in that, After obtaining the point cloud data of the area to be mapped, a statistical analysis is performed on the neighborhood of each point to calculate its average distance to all neighboring points. Points whose average distance is outside the standard range are removed from the data.

3. The mapping method based on point cloud data according to claim 1, characterized in that, The ground point extraction process is as follows: potential ground seed points are obtained using morphological methods; accurate ground seed points are obtained from the potential ground seed points; a TIN-based model is constructed using the accurate ground seed points and the TIN is iteratively encrypted to extract ground points; and finally, the ground points are normalized.

4. The mapping method based on point cloud data according to claim 1, characterized in that, Ground point segmentation specifically involves dividing ground points into vegetation point clouds and road point clouds. The boundary extraction process is as follows: perform planar projection on the road point cloud and vegetation point cloud respectively, extract the boundary and draw lines. Take any two points p1 and p2 in the point set S, and draw a circle with radius α through these two points. If there are no other points in the circle, then p1p2 is the boundary line, until all points are calculated.

5. The mapping method based on point cloud data according to claim 1, characterized in that, The process of extracting buildings from non-ground points is as follows: non-ground point clouds are obtained by segmenting ground points. Two parameters, neighborhood radius and minimum number of neighborhood points, are set to represent the density of the point cloud. Points that can reach the minimum number of neighborhood points within the range defined by the neighborhood radius are set as core points. Clusters are continuously expanded from the core points to achieve clustering of clusters of arbitrary shapes, thereby extracting buildings.

6. The mapping method based on point cloud data according to claim 1, characterized in that, The process of extracting wall point cloud through multi-plane segmentation is as follows: the building point cloud C0 is segmented into multiple planes using the random sampling consensus algorithm, and then the angle threshold is set to extract the wall information of the building.

7. The mapping method based on point cloud data according to claim 1, characterized in that, The extracted point cloud of the building walls is projected onto a plane to obtain the building's outline points. The outline points are then simplified using feature preservation. Finally, a model-based outline fitting is performed, employing the Random Sample Consensus (RANSAC) algorithm to calculate the model parameters for each sample set. The distance from each point to the model is then calculated, and points with a distance less than the threshold are designated as inliers. After a large number of samples, the model with the most inliers is selected as the extraction result, and its inliers represent the segmentation result corresponding to the extraction model. This process is repeated to complete one segmentation cycle. RANSAC is then iteratively executed to segment the model from the remaining point set, achieving the segmentation of all outline points. Finally, outline fitting is performed based on the model parameters, and lines are drawn to obtain the final building outline.

8. A mapping system based on point cloud data, characterized in that, include: The point cloud data acquisition module is used to acquire point cloud data of the area to be mapped. The ground point processing module is used to extract, segment, and extract boundaries of ground points in point cloud data to obtain ground contour lines; The non-ground point processing module is used to extract buildings from non-ground points in point cloud data, extract wall point clouds by multi-plane segmentation of buildings, obtain the outline points of buildings by planar projection of wall point clouds, and fit them to obtain the outline of buildings. The topographic map generation module is used to merge ground outlines and building outlines to obtain the final topographic map.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the mapping method based on point cloud data as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the mapping method based on point cloud data as described in any one of claims 1 to 7.

Images