A computing method and device based on point cloud data

Abstract

The embodiment of the present application provides a kind of based on point cloud data's computing method and device, it is related to data processing technical field.The method comprises: obtaining original three-dimensional point cloud data and the coordinates of specified cubic region;Based on the coordinates of the specified cubic region, obtain initial three-dimensional point cloud data from the original three-dimensional point cloud data;Based on the initial three-dimensional point cloud data, cubic three-dimensional point cloud data is segmented, and at least one target cubic three-dimensional point cloud data is obtained;The at least one target cubic three-dimensional point cloud data is merged with the initial three-dimensional point cloud data, and target three-dimensional point cloud data is obtained;Obtain the plurality of microelement layers corresponding to the target three-dimensional point cloud data;The volume of the plurality of microelement layers is obtained, and the volume of each microelement layer is added to obtain the volume corresponding to the target three-dimensional point cloud data.The embodiment of the present application is used to improve the precision when calculating volume based on point cloud data.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, specifically to a calculation method and apparatus based on point cloud data. Background Technology

[0002] Currently, in the field of point cloud data computing, point cloud data of the surface of a target object can be collected using various technologies to construct a 3D model of the target object, and then various information about the target object can be obtained through the 3D model. For example, information such as the volume of the target object can be calculated from the point cloud data in the 3D model.

[0003] However, when calculating the volume of a target object using point cloud data from a 3D model, the collected point cloud data is often incomplete or missing, leading to an inaccurate 3D model of the target object. Consequently, the calculated volume of the target object will have errors, affecting subsequent analysis and applications. Therefore, how to improve the accuracy of obtaining the volume of a target object based on point cloud data has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, embodiments of this application provide a calculation method and apparatus based on point cloud data to improve the accuracy of volume calculation based on point cloud data.

[0005] In a first aspect, embodiments of this application provide a calculation method based on point cloud data, including:

[0006] Obtain the original 3D point cloud data and the coordinates of a specified cube region; the coordinates of the specified cube region are obtained based on a spatial rectangular coordinate system; the spatial rectangular coordinate system is established based on the acquisition scene corresponding to the original 3D point cloud data, the xoy plane formed by the x-axis and y-axis in the spatial rectangular coordinate system is parallel to the ground, the z-axis is vertically upward, and the xoy, yoz, and xoz planes are perpendicular to each other;

[0007] Based on the coordinates of the specified cube region, initial 3D point cloud data is obtained from the original 3D point cloud data; the initial 3D point cloud data is the original 3D point cloud data within the specified cube region.

[0008] Based on the initial 3D point cloud data, the cube 3D point cloud data is segmented to obtain at least one target cube 3D point cloud data; the cube 3D point cloud data is the cube outer surface 3D point cloud data generated based on the coordinates of the specified cube region.

[0009] The three-dimensional point cloud data of the at least one target cube is merged with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data;

[0010] Obtain multiple micro-layers corresponding to the target 3D point cloud data;

[0011] The volumes of the multiple micro-layers are obtained, and the volumes of each micro-layer are added together to obtain the volume corresponding to the target 3D point cloud data.

[0012] As an optional implementation of this application, the step of segmenting the cube's 3D point cloud data based on the initial 3D point cloud data to obtain at least one target cube's 3D point cloud data includes:

[0013] Obtain the overlapping portion of the initial 3D point cloud data and the cube 3D point cloud data to generate the first 3D point cloud data;

[0014] Delete the first three-dimensional point cloud data in the cube three-dimensional point cloud data to obtain the cube point cloud data to be segmented;

[0015] The target Euclidean clustering segmentation algorithm is used to segment the point cloud data of the cube to be segmented, thereby obtaining the three-dimensional point cloud data of the at least one target cube.

[0016] As an optional implementation of this application, before segmenting the cube point cloud data to be segmented based on the target Euclidean clustering segmentation algorithm to obtain the at least one target cube 3D point cloud data, the method further includes:

[0017] Based on the resolution of the original 3D point cloud data, the preset parameters corresponding to the initial Euclidean clustering segmentation algorithm are adjusted to obtain the target Euclidean clustering segmentation algorithm.

[0018] As an optional implementation of this application, the step of merging the at least one target cube 3D point cloud data with the initial 3D point cloud data to obtain target 3D point cloud data includes:

[0019] The initial 3D point cloud data is projected onto the xoy plane, and at least one planar boundary corresponding to the initial 3D point cloud data is obtained based on the boundary extraction algorithm.

[0020] Project the three-dimensional point cloud data of the at least one target cube onto the xoy plane to obtain at least one planar point cloud data corresponding to the three-dimensional point cloud data of the at least one target cube;

[0021] For each planar point cloud data in the at least one planar point cloud data, if there are more than a preset number of points within the planar boundary, then the partial cubic 3D point cloud data corresponding to the planar point cloud data is merged with the initial 3D point cloud data to obtain the target 3D point cloud data.

[0022] As an optional implementation of this application, the step of obtaining multiple micro-layers corresponding to the target 3D point cloud data includes:

[0023] Obtain the value range of the target 3D point cloud data in a preset direction;

[0024] The value range is divided into multiple micro-elements according to a preset interval length;

[0025] Based on the multiple micro-elements, the target 3D point cloud data is divided into multiple micro-element layers from the preset direction.

[0026] As an optional implementation of this application, the step of obtaining the volume of the plurality of micro-layers and adding the volumes of the individual micro-layers to obtain the volume corresponding to the target 3D point cloud data includes:

[0027] For each of the plurality of micro-layers, the point cloud data in the micro-layer is projected onto the xoy plane to obtain the planar point cloud data of the micro-layer.

[0028] Based on the planar point cloud data of the micro-element layer, the boundary points of the planar point cloud data of the micro-element layer are obtained. Any one of the boundary points is taken as the starting boundary point, and the boundary points of the micro-element layer are sorted according to a preset direction to obtain the sequential boundary points.

[0029] Starting from the initial boundary point, multiple triangles are sequentially obtained based on the sequential boundary points, consisting of the boundary point, the next boundary point of the boundary point, and the centroid of the micro-element layer.

[0030] The areas of the multiple triangles are obtained and summed to obtain the planar area of ​​the micro-element layer;

[0031] The volume of the micro-element layer is obtained by multiplying its planar area by its height.

[0032] The volumes of each micro-element layer are added together to obtain the volume corresponding to the target 3D point cloud data.

[0033] As an optional implementation of this application, the method further includes:

[0034] Adjust the preset distance according to the resolution of the original 3D point cloud data;

[0035] The preset interval length is adjusted according to the resolution of the original 3D point cloud data.

[0036] Secondly, embodiments of this application provide a computing device based on point cloud data, including:

[0037] The first acquisition unit is used to acquire the original 3D point cloud data and the specified cubic region;

[0038] A processing unit is configured to obtain initial 3D point cloud data from the original 3D point cloud data based on the coordinates of the specified cube region; the initial 3D point cloud data is the original 3D point cloud data within the specified cube region.

[0039] The segmentation unit is used to segment the cube 3D point cloud data based on the initial 3D point cloud data to obtain at least one target cube 3D point cloud data; the cube 3D point cloud data is the cube outer surface 3D point cloud data generated based on the coordinates of the specified cube region;

[0040] The merging unit is used to merge the three-dimensional point cloud data of the at least one target cube with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data;

[0041] The second acquisition unit acquires multiple micro-layers corresponding to the target three-dimensional point cloud data;

[0042] An accumulation unit is used to obtain the volume of the multiple micro-layers and add the volumes of each micro-layer to obtain the volume corresponding to the target three-dimensional point cloud data.

[0043] As an optional implementation of this application, the segmentation unit is specifically used to obtain the overlapping part of the initial three-dimensional point cloud data and the cube three-dimensional point cloud data to generate first three-dimensional point cloud data; delete the first three-dimensional point cloud data in the cube three-dimensional point cloud data to obtain cube point cloud data to be segmented; and segment the cube point cloud data to be segmented based on the target Euclidean clustering segmentation algorithm to obtain at least one target cube three-dimensional point cloud data.

[0044] As an optional implementation of this application, the segmentation unit is further configured to adjust the preset parameters corresponding to the initial Euclidean clustering segmentation algorithm according to the resolution of the original three-dimensional point cloud data, so as to obtain the target Euclidean clustering segmentation algorithm.

[0045] As an optional implementation of this application, the merging unit is specifically used to project the initial three-dimensional point cloud data onto the xoy plane and obtain at least one planar boundary corresponding to the initial three-dimensional point cloud data based on a boundary extraction algorithm; project the at least one target cube three-dimensional point cloud data onto the xoy plane to obtain at least one planar point cloud data corresponding to the at least one target cube three-dimensional point cloud data; for each planar point cloud data in the at least one planar point cloud data, if there are more than a preset number of points in the planar point cloud data within the planar boundary, then merge the portion of the cube three-dimensional point cloud data corresponding to the planar point cloud data with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data.

[0046] As an optional implementation of this application, the second acquisition unit specifically acquires the value range of the target three-dimensional point cloud data in a preset direction; divides the value range into multiple micro-elements according to a preset interval length; and divides the target three-dimensional point cloud data into multiple micro-element layers from the preset direction based on the multiple micro-elements.

[0047] As an optional implementation of this application, the accumulation unit is specifically used to: project the point cloud data in each of the plurality of micro-layers onto the xoy plane to obtain planar point cloud data of the micro-layer; obtain the boundary points of the planar point cloud data of the micro-layer based on the planar point cloud data of the micro-layer; take any one of the boundary points as the starting boundary point and sort the boundary points of the micro-layer according to a preset direction to obtain sequential boundary points; starting from the starting boundary point, obtain a plurality of triangles formed by the boundary point, the next boundary point of the boundary point, and the centroid of the micro-layer in sequence based on the sequential boundary points; obtain the area of ​​the plurality of triangles and accumulate them to obtain the planar area of ​​the micro-layer; multiply the planar area of ​​the micro-layer by the height of the micro-layer to obtain the volume of the micro-layer; and add the volumes of each micro-layer to obtain the volume corresponding to the target three-dimensional point cloud data.

[0048] As an optional implementation of this application, the processing unit is further configured to adjust a preset distance according to the resolution of the original three-dimensional point cloud data; and to adjust a preset interval length according to the resolution of the original three-dimensional point cloud data.

[0049] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to cause the electronic device to implement the point cloud data-based calculation method described in any of the above embodiments when executing the computer program.

[0050] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a computing device, causes the computing device to implement the point cloud data-based calculation method described in any of the above embodiments.

[0051] Fifthly, embodiments of this application provide a computer program product that, when run on a computer, enables the computer to implement the point cloud data-based calculation method described in the third or fourth aspect.

[0052] The calculation method based on point cloud data provided in this application embodiment specifically includes: acquiring the original 3D point cloud data and the coordinates of a specified cube region; the coordinates of the specified cube region are acquired based on a spatial rectangular coordinate system; the spatial rectangular coordinate system is established based on the acquisition scene corresponding to the original 3D point cloud data, wherein the xoy plane formed by the x-axis and y-axis in the spatial rectangular coordinate system is parallel to the ground, the z-axis is vertically upward, and the xoy, yoz, and xoz planes are perpendicular to each other; based on the coordinates of the specified cube region, initial 3D point cloud data is acquired from the original 3D point cloud data; the initial 3D point cloud data is acquired from the specified cube region. The original 3D point cloud data within a cube region; the cube 3D point cloud data is segmented based on the initial 3D point cloud data to obtain at least one target cube 3D point cloud data; the cube 3D point cloud data is the cube outer surface 3D point cloud data generated based on the coordinates of the specified cube region; the at least one target cube 3D point cloud data is merged with the initial 3D point cloud data to obtain target 3D point cloud data; multiple micro-layers corresponding to the target 3D point cloud data are obtained; the volumes of the multiple micro-layers are obtained, and the volumes of each micro-layer are added together to obtain the volume corresponding to the target 3D point cloud data. In this embodiment, the initial 3D point cloud data is supplemented using the at least one cube 3D point cloud data to ensure the integrity of the point cloud data, and then the target 3D point cloud data is divided into several micro-layers. The volume of each micro-layer is calculated and accumulated to obtain the total volume of the target object, thereby improving the accuracy of volume calculation based on point cloud data. Attached Figure Description

[0053] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings that need to be called in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is one of the flowcharts of the calculation method based on point cloud data provided in the embodiments of this application;

[0056] Figure 2 One of the scenario illustrations for the point cloud data-based calculation method provided in the embodiments of this application;

[0057] Figure 3 A second schematic diagram illustrating a scenario for the point cloud data-based computation method provided in this application embodiment;

[0058] Figure 4 The second flowchart of the calculation method based on point cloud data provided in the embodiments of this application;

[0059] Figure 5 The third step of the calculation method based on point cloud data provided in the embodiments of this application;

[0060] Figure 6 A scene diagram illustrating the point cloud data-based computation method provided in this application embodiment;

[0061] Figure 7 A schematic diagram of the structure of a point cloud data-based computing device provided in an embodiment of this application;

[0062] Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0063] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0064] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0065] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0066] It should be noted that, in this document, the term "comprising" or any other variation thereof is 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 a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0067] The point cloud data-based calculation method in this application embodiment can be compiled into Webassembly bytecode by Emscripten (an encoder) using a C++ code file containing a Point Cloud Library (PCL), so as to achieve point cloud measurement at the fastest speed on the browser side.

[0068] Emscripten is a compiler based on the Low Level Virtual Machine (LLVM). It can compile C / C++ code into JavaScript code, but not ordinary JavaScript; rather, it's a JavaScript variant called asm.js (a subset of JavaScript with "highly optimizable" instructions). Using this method, the point cloud data-based computation method provided in this application can be compiled into the browser and run on the CPU at near-native speed. This code is in binary form and can be directly used as modules in JavaScript. WebAssembly is a new type of code that runs in modern web browsers, offering new performance features and effects.

[0069] Based on the above, this application provides a calculation method based on point cloud data, referring to... Figure 1 As shown, the calculation method based on point cloud data includes the following steps S101-S106:

[0070] S101. Obtain the original 3D point cloud data and the coordinates of the specified cube region.

[0071] The coordinates of the specified cube region are obtained based on a spatial rectangular coordinate system. The spatial rectangular coordinate system is established based on the acquisition scene corresponding to the original three-dimensional point cloud data. The xoy plane formed by the x-axis and y-axis in the spatial rectangular coordinate system is parallel to the ground, the z-axis is vertically upward, and the xoy, yoz, and xoz planes are perpendicular to each other.

[0072] In some embodiments, the original 3D point cloud data can be acquired using existing technologies. For example, images of the target area can be acquired using various existing devices such as laser scanners (LiDAR Light Detection and Ranging), stereo cameras, and depth cameras to obtain the original 3D point cloud data. For instance, the laser 3D scanner utilizes the principle of laser ranging. By recording the 3D coordinates, reflectivity, and texture information of a large number of dense points on the surface of the object being measured, it can quickly reconstruct the 3D model of the target object and various graphic data such as lines, surfaces, and volumes. It is mainly used in reverse engineering, responsible for surface digitization and 3D measurement of workpieces. For existing 3D physical objects (samples or models) without technical documentation, it can quickly measure the contour set data of the object, and then construct, edit, and modify it to generate a digital surface model in a universal output format.

[0073] In this embodiment of the application, information can be collected from the target area using any of the existing methods described above to generate the original three-dimensional point cloud data.

[0074] In some embodiments, the coordinates of the specified cube region are obtained based on a user-specified cube region. The user can set a cube region of a specified size to obtain the original 3D point cloud data of the cube region of the specified size. Specifically, the coordinates of the specified cube region are obtained through the specified cube region, so as to obtain the 3D point cloud data of the specified cube region from the original 3D point cloud data through the coordinates of the specified cube region.

[0075] In some embodiments, prior to step S101 above, the calculation method based on point cloud data provided in this application embodiment further includes the following steps:

[0076] Obtain the viewpoint direction of the original 3D point cloud data, and adjust the viewpoint direction of the cube 3D point cloud data to the viewpoint direction of the original 3D point cloud data.

[0077] Specifically, the viewing direction of the original 3D point cloud data is acquired, and then the viewing direction of the cube 3D point cloud data is adjusted to the viewing direction of the original 3D point cloud data for subsequent analysis and calculation.

[0078] S102. Based on the coordinates of the specified cube region, obtain initial three-dimensional point cloud data from the original three-dimensional point cloud data.

[0079] For example, refer to Figure 2 As shown, when the original three-dimensional point cloud data is a sphere, if the volume of half a sphere is to be obtained, the three-dimensional point cloud data of half a sphere can be extracted by constructing a cube 21 through the coordinates of the specified cube region, and the three-dimensional point cloud data 22 in the cube 21 of the original three-dimensional point cloud data can be obtained, that is, the three-dimensional point cloud data of half a sphere.

[0080] S103. Based on the initial three-dimensional point cloud data, the cube three-dimensional point cloud data is segmented to obtain at least one target cube three-dimensional point cloud data.

[0081] The cube 3D point cloud data is generated based on the coordinates of the specified cube region, and is the cube outer surface 3D point cloud data.

[0082] In some embodiments, the cubic 3D point cloud data is used to fill in the missing areas of the initial 3D point cloud data to ensure that the final 3D point cloud data used for volume calculation is a closed point cloud data, thereby improving the accuracy of volume calculation.

[0083] S104. Merge the three-dimensional point cloud data of the at least one target cube with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data.

[0084] In some embodiments, the three-dimensional point cloud data of the at least one target cube is merged with the original three-dimensional point cloud data to complete the original three-dimensional point cloud data, ensuring that the final three-dimensional point cloud data used for volume calculation is the closed acquisition target three-dimensional point cloud data.

[0085] In some embodiments, prior to step S103 above, the calculation method based on point cloud data may further include:

[0086] Voxel filtering is performed on the original 3D point cloud data.

[0087] In some embodiments, the method for performing voxel filtering on the original 3D point cloud data can be as follows: Data voxelization is achieved through PCL point cloud downsampling, reducing the number of points and the amount of point cloud data, while simultaneously preserving the shape characteristics of the point cloud. This is very practical in improving the speed of algorithms such as registration, surface reconstruction, and shape recognition. Voxel filters can achieve downsampling without destroying the geometry of the point cloud itself, but they will shift the position of the points. Furthermore, voxel filters can remove a certain degree of noise and outliers, making the point cloud data more accurate; their main function is for downsampling.

[0088] Specifically, the principle of voxel filtering is as follows: based on the input point cloud, first, a cube that can just enclose the point cloud is calculated; then, according to the set resolution, the large cube is divided into different smaller cubes. For points within each small cube, their centroids are calculated, and the coordinates of these centroids are used to approximate several points within the cube.

[0089] S105. Obtain multiple micro-layers corresponding to the target three-dimensional point cloud data.

[0090] For example, the maximum and minimum values ​​of the target 3D point cloud data in the z-axis direction can be obtained, that is, the coordinates of the positions of the largest and smallest points on the positive and negative half-axis of the z-axis can be obtained, the value range of the target 3D point cloud data in the z-axis direction can be determined, and then based on the value range of the target 3D point cloud data in the z-axis direction, several micro-layers can be obtained from the target 3D point cloud data based on the value range of the z-axis using a pass-through filter.

[0091] For example, refer to Figure 3 The diagram shown illustrates how the target 3D point cloud data is divided into multiple micro-layers according to an embodiment of this application. Taking the original 3D point cloud data as a sphere as an example, multiple micro-layers can be obtained according to the division method shown in the diagram. The volume of each micro-layer is calculated, and the volumes of each micro-layer are added together to obtain the volume of the entire sphere.

[0092] S106. Obtain the volume of the plurality of micro-layers, and add the volumes of each micro-layer to obtain the volume corresponding to the target three-dimensional point cloud data.

[0093] In some embodiments, after obtaining the closed target 3D point cloud data, the target 3D point cloud data is divided into multiple micro-layers, and the total volume of the multiple micro-layers is calculated to obtain the volume corresponding to the target 3D point cloud data.

[0094] The calculation method based on point cloud data provided in this application embodiment specifically includes: acquiring the original 3D point cloud data and the coordinates of a specified cube region; the coordinates of the specified cube region are acquired based on a spatial rectangular coordinate system; the spatial rectangular coordinate system is established based on the acquisition scene corresponding to the original 3D point cloud data, wherein the xoy plane formed by the x-axis and y-axis in the spatial rectangular coordinate system is parallel to the ground, the z-axis is vertically upward, and the xoy, yoz, and xoz planes are perpendicular to each other; based on the coordinates of the specified cube region, initial 3D point cloud data is acquired from the original 3D point cloud data; the initial 3D point cloud data is acquired from the specified cube region. The original 3D point cloud data within the cube region; the cube 3D point cloud data is segmented based on the initial 3D point cloud data to obtain at least one target cube 3D point cloud data; the cube 3D point cloud data is the cube outer surface 3D point cloud data generated based on the coordinates of the specified cube region; the at least one target cube 3D point cloud data is merged with the initial 3D point cloud data to obtain target 3D point cloud data; multiple micro-layers corresponding to the target 3D point cloud data are obtained; the volumes of the multiple micro-layers are obtained, and the volumes of each micro-layer are added together to obtain the volume corresponding to the target 3D point cloud data. In this embodiment, the initial 3D point cloud data is supplemented using at least one target cube 3D point cloud data to ensure the integrity of the point cloud data. The target 3D point cloud data is then divided into several micro-layers, the volume of each micro-layer is calculated and accumulated to obtain the total volume of the target object, thereby improving the accuracy of volume calculation based on point cloud data.

[0095] As an extension and refinement of the above embodiments, this application provides a calculation method based on point cloud data, referring to... Figure 4 As shown, the calculation method based on point cloud data includes the following steps S401 to S408:

[0096] S401. Obtain the original 3D point cloud data and the coordinates of the specified cube region.

[0097] The coordinates of the specified cube region are obtained based on a spatial rectangular coordinate system. The spatial rectangular coordinate system is established based on the acquisition scene corresponding to the original three-dimensional point cloud data. The xoy plane formed by the x-axis and y-axis in the spatial rectangular coordinate system is parallel to the ground, the z-axis is vertically upward, and the xoy, yoz, and xoz planes are perpendicular to each other.

[0098] S402. Based on the coordinates of the specified cube region, obtain initial three-dimensional point cloud data from the original three-dimensional point cloud data.

[0099] The initial three-dimensional point cloud data is the original three-dimensional point cloud data within the specified cubic region.

[0100] S403. Obtain the overlapping portion of the initial three-dimensional point cloud data and the cube three-dimensional point cloud data to generate the first three-dimensional point cloud data.

[0101] In some embodiments, the overlapping portion of the initial 3D point cloud data and the cube 3D point cloud data is the intersection of the initial 3D point cloud data and the cube 3D point cloud data. The purpose is to use the overlapping portion, i.e., the first 3D point cloud data, to segment the cube 3D point cloud data and complete the initial 3D point cloud data to obtain a closed 3D point cloud data.

[0102] Specifically, the overlapping portion of the initial 3D point cloud data and the cube 3D point cloud data can be obtained through the following method:

[0103] For each point cloud data in the initial three-dimensional point cloud data, point cloud data within a preset distance range that is in the cube point cloud data is determined to obtain the overlapping portion.

[0104] For example, the preset distance can be 1 cm. Then, for each point of the initial three-dimensional point cloud data, the points of the cube point cloud data within a 1 cm radius around it are obtained. If there is a point 1 of the cube point cloud data within a 1 cm radius around it, then point 1 is determined to be an overlapping point. The above method is used to traverse all points in the initial three-dimensional point cloud data to find all overlapping points, so as to obtain the overlapping part of the initial three-dimensional point cloud data and the cube three-dimensional point cloud data.

[0105] It should be noted that the preset distance can be adaptively set according to the resolution of the original 3D point cloud data. Specifically, the resolution of the point cloud data reflects the density of the original 3D point cloud data and can be represented by the distance between two points. A specific method for calculating the resolution of the original 3D point cloud data may include: first, traversing every point in the 3D point cloud data, finding the nearest point to that point, calculating the distance between the two points, summing the distances, and dividing by the number of points in the point cloud (excluding invalid points). The result is the point cloud spatial resolution; the higher the resolution, the sparser the points in the point cloud data.

[0106] In some embodiments, the density of the original 3D point cloud data can be determined based on its resolution. The corresponding preset distance is then adaptively set according to the density of the point cloud data. When the resolution of the point cloud data is high, i.e., the point cloud data is relatively sparse, the preset distance can be increased. Conversely, when the resolution of the point cloud data is low, i.e., the point cloud data is relatively dense, the preset distance can be decreased. This avoids unnecessary errors and inaccurate calculation results when using the same preset distance for different point cloud data densities.

[0107] S404. Delete the first three-dimensional point cloud data in the cube three-dimensional point cloud data to obtain the cube point cloud data to be segmented.

[0108] In some embodiments, after deleting the first three-dimensional point cloud data from the cube three-dimensional point cloud data, only the points that do not overlap with the initial three-dimensional point cloud data remain in the cube point cloud data, which is the cube point cloud data to be segmented.

[0109] S405. Based on the target Euclidean clustering segmentation algorithm, segment the cube point cloud data to be segmented to obtain the three-dimensional point cloud data of the at least one target cube.

[0110] In some embodiments, the target Euclidean clustering segmentation algorithm is a clustering algorithm based on Euclidean distance metric. Typically, when using the Euclidean clustering algorithm, it is combined with the K-dimension Tree algorithm to analyze and process the cubic point cloud data to be segmented.

[0111] Specifically, firstly, a K-dimensional tree representation of the cube point cloud data to be segmented is generated, and an empty table M and a threshold radius R are pre-set. Then, for each point in the cube point cloud data to be segmented, a nearest neighbor search is performed to obtain the n nearest neighbors of that point. For example, the n nearest neighbors of point A in the cube point cloud data to be segmented are obtained. Then, the distances of these n points to point A are determined. Points whose distances are less than the threshold radius R are placed in table M, and a nearest neighbor search is also performed for each point in table M. The above steps are repeated to traverse all points in the cube point cloud data to be segmented until no new points are added to table M. Finally, based on the points in table M, the 3D point cloud data of at least one target cube can be determined, laying the foundation for subsequent completion of the original 3D point cloud data.

[0112] Before segmenting the cube point cloud data to be segmented based on the target Euclidean clustering segmentation algorithm in step S405 above, and obtaining the three-dimensional point cloud data of the at least one target cube, the calculation method based on point cloud data further includes the following steps:

[0113] Based on the resolution of the original 3D point cloud data, the preset parameters corresponding to the initial Euclidean clustering segmentation algorithm are adjusted to obtain the target Euclidean clustering segmentation algorithm.

[0114] In some embodiments, the density of the original 3D point cloud data can be determined based on its resolution. Corresponding preset parameters are then set according to the density of the point cloud data to obtain the target Euclidean clustering algorithm. Specifically, the search radius of the point cloud data can be set according to the resolution. When the resolution of the point cloud data is large, i.e., the point cloud data is relatively sparse, the search radius can be increased to ensure the effectiveness of the results obtained from the analysis and processing based on the Euclidean clustering algorithm. When the resolution of the point cloud data is small, i.e., the point cloud data is relatively dense, the search radius can be decreased to avoid too many points appearing when searching for surrounding point cloud data for a single point cloud, which could easily lead to errors.

[0115] S406. Merge the three-dimensional point cloud data of the at least one target cube with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data.

[0116] In some embodiments, the implementation method of step S406 (merging the at least one target cube 3D point cloud data with the initial 3D point cloud data to obtain target 3D point cloud data) can refer to steps one to three as follows:

[0117] Step 1: Project the initial 3D point cloud data onto the xoy plane, and obtain at least one planar boundary corresponding to the initial 3D point cloud data based on the boundary extraction algorithm.

[0118] In some embodiments, after projecting the initial 3D point cloud data onto the xoy plane, the boundary of the initial 3D point cloud data is obtained using the boundary extraction algorithm. For example, the boundary extraction algorithm can be an existing boundary extraction method such as latitude and longitude scanning, mesh generation, or normal estimation.

[0119] Step 2: Project the three-dimensional point cloud data of the at least one target cube onto the xoy plane to obtain at least one planar point cloud data corresponding to the three-dimensional point cloud data of the at least one target cube.

[0120] Step 3: For each planar point cloud data in the at least one planar point cloud data, if there are more than a preset number of points in the planar point cloud data within the corresponding planar boundary, then merge the partial cubic 3D point cloud data corresponding to the planar point cloud data with the initial 3D point cloud data to obtain the target 3D point cloud data.

[0121] In some embodiments, after projecting the three-dimensional point cloud data of the at least one target cube onto the xoy plane based on step two above, point cloud data of the plane to be used is obtained. Then, by comparing whether the point cloud data of the plane to be used is within the plane boundary corresponding to the initial three-dimensional point cloud data, it can be clearly determined whether the point cloud data of the plane to be used is the point cloud data of the target object.

[0122] In some embodiments, the preset quantity is based on the current quantity of planar point cloud data to be used, which can be obtained by multiplying the quantity of planar point cloud data to be used by a preset value. The preset value can be set to 90% or 95%; this application embodiment does not limit this.

[0123] Specifically, if 95% of the points in the planar point cloud data A are within the planar boundary a corresponding to the initial 3D point cloud data, then the planar point cloud data A belongs to the target 3D point cloud data. The initial planar point cloud data and the partial cubic point cloud data corresponding to the planar point cloud data A are merged to obtain the completed 3D point cloud data, which is the target 3D point cloud data.

[0124] S407. Obtain multiple micro-layers corresponding to the target three-dimensional point cloud data.

[0125] In step S407 above, the specific method for obtaining the multiple micro-layers corresponding to the target 3D point cloud data can be referred to steps 1 to 3 below:

[0126] Step 1: Obtain the value range of the target 3D point cloud data in a preset direction.

[0127] In some embodiments, the maximum and minimum points of the target 3D point cloud data in the z-axis direction can be obtained, and the values ​​of the maximum and minimum points in the z-axis direction can be obtained, that is, the value range in the z-axis direction can be generated.

[0128] Step 2: Divide the value range into multiple micro-elements according to the preset interval length.

[0129] In some embodiments, when the value range is [0-10] and the preset interval length is 1 unit, the value range [0-10] can be divided into 10 micro-elements with an interval length of 1. It should be noted that the preset interval length can be adaptively adjusted according to the resolution of the original 3D point cloud data. Specific steps are as follows:

[0130] The preset interval length is adjusted according to the resolution of the original 3D point cloud data.

[0131] In some embodiments, the density of the original 3D point cloud data can be determined based on its resolution. A corresponding preset interval length is then set according to the density of the point cloud data. When the resolution of the point cloud data is high (i.e., the point cloud data is relatively sparse), the preset interval length needs to be adaptively increased. Conversely, when the resolution of the point cloud data is low (i.e., the point cloud data is relatively dense), the preset interval length needs to be adaptively decreased. This ensures that the multiple micro-layers obtained by dividing the data according to the preset interval length are reasonable, preventing large errors and improving the accuracy of subsequent calculations. Specifically, the preset interval length can also be 1.5 times the resolution of the original 3D point cloud data as the preset interval length for dividing the micro-layers.

[0132] Step 3: Based on the multiple micro-elements, divide the target 3D point cloud data into multiple micro-element layers from the preset direction.

[0133] In conjunction with the embodiment of step 2 above, after dividing the value range [0-10] into 10 micro-elements, the target three-dimensional point cloud data is then divided into 10 micro-element layers according to the 10 micro-elements.

[0134] S408. Obtain the volume of the plurality of micro-layers, and add the volumes of each micro-layer to obtain the volume corresponding to the original target three-dimensional point cloud data.

[0135] As an extension and refinement of the above embodiments, refer to Figure 5 As shown, the implementation method of step S408 (obtaining the volume of the plurality of micro-layers and adding the volumes of each micro-layer to obtain the volume corresponding to the target 3D point cloud data) may include the following steps S401-S406:

[0136] S501. For each of the plurality of micro-layers, project the point cloud data in the micro-layer onto the xoy plane to obtain the planar point cloud data of the micro-layer.

[0137] In some embodiments, each of the plurality of micro-layers is projected onto the xoy plane to obtain planar point cloud data for each of the plurality of micro-layers.

[0138] S502. Obtain the boundary points of the planar point cloud data of the micro-element layer based on the planar point cloud data of the micro-element layer, take any one of the boundary points as the starting boundary point, sort the boundary points of the micro-element layer according to the preset direction, and obtain the sequential boundary points.

[0139] For example, refer to Figure 6As shown, the planar point cloud data of a micro-element layer is obtained by projecting the micro-element layer onto the xoy plane, where point P is the centroid of the micro-element layer, and the preset direction is counterclockwise. The sequential boundary points of the planar point cloud data of the micro-element layer are obtained as: points 1, 2...9; the preset direction can also be clockwise, and this embodiment does not limit this.

[0140] S503. Starting from the initial boundary point, based on the sequential boundary points, obtain multiple triangles composed of the boundary point, the next boundary point of the boundary point, and the centroid of the micro-element layer.

[0141] S504. Obtain the areas of the multiple triangles and sum them up to obtain the planar area of ​​the micro-element layer.

[0142] In some embodiments, obtaining the area of ​​the plurality of triangles can be achieved using any geometric algorithm for calculating the area of ​​a triangle, as described above. Figure 6 As shown, the outermost layer consists of 9 points, from point 1 to point 9. Starting from point 1, we can obtain triangles 1P2, 2P3, ..., 9P1. By obtaining the area of ​​each of the 9 triangles and summing their surfaces, we can obtain the area corresponding to the planar point cloud data of this micro-element layer.

[0143] S505. Multiply the planar area of ​​the micro-element layer by the height of the micro-element layer to obtain the volume of the micro-element layer.

[0144] S506. Add the volumes of each micro-element layer to obtain the volume corresponding to the target three-dimensional point cloud data.

[0145] In some embodiments, after obtaining the volumes of multiple micro-layers of the target 3D point cloud data, the volumes of each micro-layer are added together to obtain the volume of the target object corresponding to the target 3D point cloud data.

[0146] In this embodiment of the application, since the Emscripten compiler is used for compilation, the calculation method based on point cloud data of this embodiment can be generated into Webassembly bytecode by the Emscripten compiler. This enables the viewing of point cloud data at a relatively fast speed based on the octree point cloud structure on the browser side, and then enables the processing and analysis of point cloud data on the browser side.

[0147] Based on the same inventive concept, as an implementation of the above method, this embodiment of the invention also provides a computing device based on point cloud data. This embodiment corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the data synchronization device in this embodiment can implement all the contents of the aforementioned method embodiment.

[0148] This application provides a computing device based on point cloud data. Figure 7 This is a schematic diagram of the structure of the point cloud-based computing device, as shown below. Figure 7 As shown, the point cloud-based computing device 700 includes:

[0149] The first acquisition unit 701 is used to acquire the original three-dimensional point cloud data and the specified cube region;

[0150] Processing unit 702 is used to obtain initial three-dimensional point cloud data from the original three-dimensional point cloud data based on the coordinates of the specified cube region; the initial three-dimensional point cloud data is the original three-dimensional point cloud data within the specified cube region;

[0151] The segmentation unit 703 is used to segment the cube 3D point cloud data based on the initial 3D point cloud data to obtain at least one target cube 3D point cloud data; the cube 3D point cloud data is the cube outer surface 3D point cloud data generated based on the coordinates of the specified cube region.

[0152] The merging unit 704 is used to merge the three-dimensional point cloud data of the at least one target cube with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data.

[0153] The second acquisition unit 705 acquires multiple micro-layers corresponding to the target three-dimensional point cloud data;

[0154] The accumulation unit 706 is used to obtain the volume of the multiple micro-layers and add the volumes of each micro-layer to obtain the volume corresponding to the target three-dimensional point cloud data.

[0155] As an optional implementation of this application, the segmentation unit 703 is specifically used to obtain the overlapping part of the initial three-dimensional point cloud data and the cube three-dimensional point cloud data to generate first three-dimensional point cloud data; delete the first three-dimensional point cloud data in the cube three-dimensional point cloud data to obtain cube point cloud data to be segmented; and segment the cube point cloud data to be segmented based on the target Euclidean clustering segmentation algorithm to obtain at least one target cube three-dimensional point cloud data.

[0156] As an optional implementation of this application, the segmentation unit 703 is further configured to adjust the preset parameters corresponding to the initial Euclidean clustering segmentation algorithm according to the resolution of the original three-dimensional point cloud data, so as to obtain the target Euclidean clustering segmentation algorithm.

[0157] As an optional implementation of this application, the merging unit 704 is specifically used to project the initial three-dimensional point cloud data onto the xoy plane and obtain at least one planar boundary corresponding to the initial three-dimensional point cloud data based on a boundary extraction algorithm; project the at least one target cube three-dimensional point cloud data onto the xoy plane to obtain at least one planar point cloud data corresponding to the at least one target cube three-dimensional point cloud data; for each planar point cloud data in the at least one planar point cloud data, if there are more than a preset number of points in the planar point cloud data within the planar boundary, then merge the part of the cube three-dimensional point cloud data corresponding to the planar point cloud data with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data.

[0158] As an optional implementation of this application, the second acquisition unit 705 specifically acquires the value range of the target three-dimensional point cloud data in a preset direction; divides the value range into multiple micro-elements according to a preset interval length; and divides the target three-dimensional point cloud data into multiple micro-element layers from the preset direction based on the multiple micro-elements.

[0159] As an optional implementation of this application, the accumulation unit 706 is specifically used to: project the point cloud data in each of the plurality of micro-layers onto the xoy plane to obtain planar point cloud data of the micro-layer; obtain the boundary points of the planar point cloud data of the micro-layer based on the planar point cloud data of the micro-layer; take any one of the boundary points as the starting boundary point and sort the boundary points of the micro-layer according to a preset direction to obtain sequential boundary points; starting from the starting boundary point, obtain a plurality of triangles formed by the boundary point, the next boundary point of the boundary point, and the centroid of the micro-layer in sequence based on the sequential boundary points; obtain the area of ​​the plurality of triangles and accumulate them to obtain the planar area of ​​the micro-layer; multiply the planar area of ​​the micro-layer by the height of the micro-layer to obtain the volume of the micro-layer; and add the volumes of the various micro-layers to obtain the volume corresponding to the target three-dimensional point cloud data.

[0160] Based on the same inventive concept, embodiments of this application also provide an electronic device. Figure 8 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application, such as... Figure 8As shown, the electronic device provided in this embodiment includes a memory 801 and a processor 802. The memory 801 is used to store computer programs; the processor 802 is used to execute the calculation method based on point cloud data provided in the above embodiment when executing the computer program.

[0161] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the computing device to implement the point cloud data-based calculation method provided in the above embodiments.

[0162] Based on the same inventive concept, the application provides a computer program product that, when run on a computer, enables the computer to implement the point cloud data-based calculation method described in the third or fourth aspect.

[0163] 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 implemented on one or more computer-usable storage media containing computer-usable program code.

[0164] The processor can 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. A general-purpose processor can be a microprocessor or any conventional processor.

[0165] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0166] Computer-readable media include both permanent and non-permanent, removable and non-removable storage media. Storage media can store information using any method or technology; the information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A calculation method based on point cloud data, characterized in that, include: Obtain the original 3D point cloud data and the coordinates of a specified cube region; the coordinates of the specified cube region are obtained based on a spatial rectangular coordinate system; the spatial rectangular coordinate system is established based on the acquisition scene corresponding to the original 3D point cloud data, the xoy plane formed by the x-axis and y-axis in the spatial rectangular coordinate system is parallel to the ground, the z-axis is vertically upward, and the xoy, yoz, and xoz planes are perpendicular to each other; Based on the coordinates of the specified cube region, initial 3D point cloud data is obtained from the original 3D point cloud data; The initial three-dimensional point cloud data is the original three-dimensional point cloud data within the specified cube region; Based on the initial 3D point cloud data, the cube 3D point cloud data is segmented to obtain at least one target cube 3D point cloud data. The cube 3D point cloud data is generated based on the coordinates of the specified cube region, resulting in 3D point cloud data of the cube's outer surface. The three-dimensional point cloud data of the at least one target cube is merged with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data; Obtain multiple micro-layers corresponding to the target 3D point cloud data; The volumes of the multiple micro-layers are obtained, and the volumes of the multiple micro-layers are added together to obtain the volume corresponding to the target 3D point cloud data; The step of segmenting the cube's 3D point cloud data based on the initial 3D point cloud data to obtain at least one target cube's 3D point cloud data includes: Obtain the overlapping portion of the initial 3D point cloud data and the cube 3D point cloud data to generate the first 3D point cloud data; Delete the first three-dimensional point cloud data in the cube three-dimensional point cloud data to obtain the cube point cloud data to be segmented; The target Euclidean clustering segmentation algorithm is used to segment the point cloud data of the cube to be segmented, and the three-dimensional point cloud data of the at least one target cube is obtained. The step of merging the three-dimensional point cloud data of the at least one target cube with the initial three-dimensional point cloud data to obtain target three-dimensional point cloud data includes: The initial 3D point cloud data is projected onto the xoy plane, and at least one planar boundary corresponding to the initial 3D point cloud data is obtained based on the boundary extraction algorithm. Project the three-dimensional point cloud data of the at least one target cube onto the xoy plane to obtain at least one planar point cloud data corresponding to the three-dimensional point cloud data of the at least one target cube; For each planar point cloud data in the at least one planar point cloud data, if there are more than a preset number of points within the planar boundary, then the partial cubic 3D point cloud data corresponding to the planar point cloud data is merged with the initial 3D point cloud data to obtain the target 3D point cloud data.

2. The method according to claim 1, before segmenting the cubic point cloud data to be segmented based on the target Euclidean clustering segmentation algorithm to obtain the at least one target cube 3D point cloud data, the method further includes: Based on the resolution of the original 3D point cloud data, the preset parameters corresponding to the initial Euclidean clustering segmentation algorithm are adjusted to obtain the target Euclidean clustering segmentation algorithm.

3. The method according to claim 1, characterized in that, The process of acquiring multiple micro-layers corresponding to the target 3D point cloud data includes: Obtain the value range of the target 3D point cloud data in a preset direction; The value range is divided into multiple micro-elements according to a preset interval length; Based on the multiple micro-elements, the target 3D point cloud data is divided into multiple micro-element layers from the preset direction.

4. The method according to claim 1, characterized in that, The step of obtaining the volume of the plurality of micro-layers and adding the volumes of the plurality of micro-layers to obtain the volume corresponding to the target 3D point cloud data includes: For each of the plurality of micro-layers, the point cloud data in the micro-layer is projected onto the xoy plane to obtain the planar point cloud data of the micro-layer. Based on the planar point cloud data of the micro-element layer, the boundary points of the planar point cloud data of the micro-element layer are obtained. Any one of the boundary points is taken as the starting boundary point, and the boundary points of the micro-element layer are sorted according to a preset direction to obtain the sequential boundary points. Starting from the initial boundary point, multiple triangles are sequentially obtained based on the sequential boundary points, consisting of the boundary point, the next boundary point of the boundary point, and the centroid of the micro-element layer. The areas of the multiple triangles are obtained and summed to obtain the planar area of ​​the micro-element layer; The volume of the micro-element layer is obtained by multiplying its planar area by its height. The volumes of the multiple micro-layers are added together to obtain the volume corresponding to the target 3D point cloud data.

5. The method according to claim 3, characterized in that, The method further includes: The preset interval length is adjusted according to the resolution of the original 3D point cloud data.

6. A computing device based on point cloud data, characterized in that, include: The first acquisition unit is used to acquire the original 3D point cloud data and the specified cubic region; The processing unit is used to obtain initial three-dimensional point cloud data from the original three-dimensional point cloud data based on the coordinates of the specified cube region; The initial three-dimensional point cloud data is the original three-dimensional point cloud data within the specified cube region; The segmentation unit is used to segment the cube three-dimensional point cloud data based on the initial three-dimensional point cloud data to obtain at least one target cube three-dimensional point cloud data. The cube 3D point cloud data is generated based on the coordinates of the specified cube region, resulting in 3D point cloud data of the cube's outer surface. The merging unit is used to merge the three-dimensional point cloud data of the at least one target cube with the initial three-dimensional point cloud data to obtain the target three-dimensional point cloud data; The second acquisition unit acquires multiple micro-layers corresponding to the target three-dimensional point cloud data; An accumulation unit is used to obtain the volume of the multiple micro-layers and add the volumes of the multiple micro-layers to obtain the volume corresponding to the target three-dimensional point cloud data; The segmentation unit is specifically used to obtain the overlapping part of the initial three-dimensional point cloud data and the cube three-dimensional point cloud data to generate first three-dimensional point cloud data; delete the first three-dimensional point cloud data in the cube three-dimensional point cloud data to obtain cube point cloud data to be segmented; and segment the cube point cloud data to be segmented based on the target Euclidean clustering segmentation algorithm to obtain at least one target cube three-dimensional point cloud data. The merging unit is specifically used to project the initial 3D point cloud data onto the xoy plane and obtain at least one planar boundary corresponding to the initial 3D point cloud data based on a boundary extraction algorithm; project the at least one target cube 3D point cloud data onto the xoy plane to obtain at least one planar point cloud data corresponding to the at least one target cube 3D point cloud data; for each planar point cloud data in the at least one planar point cloud data, if there are more than a preset number of points within the planar boundary, then merge the portion of the cube 3D point cloud data corresponding to the planar point cloud data with the initial 3D point cloud data to obtain the target 3D point cloud data.

7. An electronic device, characterized in that, include: A memory and a processor, the memory being used to store a computer program; the processor being used to cause the electronic device to implement the point cloud data-based computation method according to any one of claims 1-5 when executing the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a computing device, causes the computing device to implement the point cloud data-based computing method according to any one of claims 1-5.

Images