CN116503434B - Boundary extraction method, device and equipment of point cloud data and storage medium - Google Patents
Boundary extraction method, device and equipment of point cloud data and storage medium Download PDFInfo
- Publication number
- CN116503434B CN116503434B CN202310552077.9A CN202310552077A CN116503434B CN 116503434 B CN116503434 B CN 116503434B CN 202310552077 A CN202310552077 A CN 202310552077A CN 116503434 B CN116503434 B CN 116503434B
- Authority
- CN
- China
- Prior art keywords
- point
- boundary
- cloud data
- sub
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 43
- 239000011159 matrix material Substances 0.000 claims abstract description 106
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/162—Segmentation; Edge detection involving graph-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20072—Graph-based image processing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Generation (AREA)
- Processing Or Creating Images (AREA)
Abstract
The application discloses a boundary extraction method, a device, equipment and a storage medium of point cloud data, wherein the method comprises the steps of inputting all the point cloud data in a layout; determining a boundary range of the layout according to the range covered by all the point cloud data; establishing grids with preset density according to the boundary range, and assigning 0 to each sub-grid of the grids; respectively acquiring the number of the point cloud data of each sub-grid, and assigning the sub-grids with the number larger than the preset number as 1; defining each sub-grid and adjacent sub-grids as a matrix, and respectively acquiring assigned values of all the sub-grids in each matrix through a first preset algorithm; judging whether a value assigned to each matrix is 0 or not respectively; if so, extracting a matrix with a value of 0 and taking the matrix as an edge matrix; respectively extracting edge point sets of each edge matrix, and acquiring boundary points of all the edge point sets according to a second preset algorithm; each boundary point is connected in turn based on the layout to form a boundary of all point cloud data.
Description
Technical Field
The present application relates to the field of mapping technologies, and in particular, to a method, an apparatus, a device, and a storage medium for extracting a boundary of point cloud data.
Background
The airborne laser radar technology (Thetechnique of Light Detection AND RANGING, LIDAR) can rapidly acquire a large amount of high-precision and dense discrete point cloud data, and plays an increasingly important role in the mapping field, mechanical engineering, cultural relic modeling and live-action three-dimension. The method is widely applied to the field of modern surveying and mapping, and changes the measurement mode of single-point contact measurement in the traditional surveying and mapping. The surface point cloud data of the scanning target object can be rapidly acquired by the airborne laser radar technology, and high-quality data is provided for high-precision digital elevation model acquisition, ground feature characteristic identification, live-action three-dimensional city modeling and other applications. The point cloud boundary features are important geometric features of the expression curved surface, play a key role in model reconstruction accuracy, and therefore boundary extraction of the boundary point data area becomes an important and basic work.
The main point cloud boundary extraction algorithms at present are as follows: alpha-Shapes algorithm, scanning algorithm, convex hull algorithm, search algorithm, etc. The existing algorithm provides specific ideas and practical application for extracting the point cloud boundary in theory, but the data volume involved in extracting the point cloud boundary is huge, and along with the continuous improvement of equipment process and precision, the data volume is larger and larger, and the efficiency and quality requirements of the boundary extraction method are continuously improved. Most of the current mainstream algorithms suffer from a deficiency in one of accuracy and speed: the scanning algorithm mainly determines the outermost boundary point rapidly by a sectional scanning method, but the problem of concave inclusion cannot be solved; although the convex hull algorithm can solve the concave hull problem, a large amount of judgment operations are needed when searching the next point, so that the running speed is influenced; the searching algorithm excessively depends on the side length of a searching box, the searching direction is difficult to determine, for the characteristics with slender sharp angles, the method cannot obtain accurate results, and for the calculation results of the point sets with very uneven point distribution, the calculation results are also not ideal; according to the judging condition of the model of ALPHASHAPES algorithm, it can be found that any two points are drawn in the point set to form a circle with radius of a, if no other points are in the circle, the two points are considered as boundary points, and the connecting line is a boundary line segment, but when the number of points is large, the judging time is obviously increased.
In summary, the algorithm in the prior art has a large computational burden, which results in a reduced calculation speed or inaccurate calculation results.
Disclosure of Invention
The application mainly aims to provide a boundary extraction method, device, equipment and storage medium of point cloud data, so as to solve the problems of reduced calculation speed or inaccurate calculation result caused by a large calculation load of an algorithm in the prior art.
In order to achieve the above purpose, the present application provides the following technical solutions:
a boundary extraction method of point cloud data, the boundary extraction method comprising:
Inputting all point cloud data in the layout;
Determining the boundary range of the layout according to the range covered by all the point cloud data;
establishing grids with preset density according to the boundary range, and assigning 0 to each sub-grid of the grids;
Respectively acquiring the number of the point cloud data of each sub-grid, and assigning the sub-grids with the number larger than the preset number as 1;
defining each sub-grid and adjacent sub-grids as a matrix, and respectively acquiring assigned values of all the sub-grids in each matrix through a first preset algorithm;
Judging whether the assigned value of each matrix is 0or not;
if so, extracting a matrix with a value of 0 and taking the matrix as an edge matrix;
respectively extracting edge point sets of point cloud data in each edge matrix, and acquiring boundary points of all the edge point sets according to a second preset algorithm;
And connecting each boundary point in turn based on the layout to form boundaries of all point cloud data.
As a further improvement of the present application, defining each sub-grid and adjacent sub-grids as a matrix, and respectively obtaining the assigned values of all the sub-grids in each matrix through a first preset algorithm, including:
Defining each sub-grid and eight sub-grids adjacent to each sub-grid as a 3 x 3 matrix;
judging whether the assignment of the subgrid in each 3 multiplied by 3 matrix is 0 through a sliding window algorithm;
If not, deleting the 3×3 matrix with the value of 0 without the sub-grid.
As a further improvement of the present application, extracting edge point sets of point cloud data in each edge matrix respectively, and obtaining boundary points of all the edge point sets according to a second preset algorithm includes:
respectively calculating a row-column value of each point cloud data in each edge matrix and establishing a lattice to be communicated for each point cloud data according to a Krueskal algorithm;
Obtaining the minimum spanning tree of the lattice to be communicated according to the Krueskal algorithm;
extracting point cloud data in the minimum spanning tree and taking the point cloud data as the edge point set;
Acquiring point cloud data with the smallest y value in the edge point set as a first boundary point based on the y direction of the grid;
Acquiring point cloud data in a first radius range preset by the first boundary point as a first candidate point;
Connecting each first candidate point with the first boundary point to form a first candidate line segment;
Acquiring first candidate points with the largest included angles with the y direction in all the first candidate line segments as second boundary points;
and continuously acquiring a first candidate point with the largest included angle with the y direction in all first candidate line segments based on the current boundary point as the next boundary point on the basis of the previous boundary point.
As a further improvement of the present application, acquiring point cloud data located within a preset first radius range of the first boundary point as a first candidate point, and then includes:
judging first uniformity of point cloud data in the preset first radius range of the first boundary point;
If the first uniformity is smaller than or equal to a first preset threshold value, acquiring two point cloud data closest to the first boundary point as two second candidate points;
connecting each second candidate point with the first boundary point to form a second candidate line segment;
judging whether the ratio of a shorter line segment to a longer line segment in the two second candidate line segments is smaller than or equal to a preset ratio;
If yes, selecting a second candidate point corresponding to the shorter line segment as the next boundary point.
As a further improvement of the present application, determining whether the ratio of the shorter line segment to the longer line segment in the two second candidate line segments is equal to or smaller than a preset ratio, includes:
If not, continuously acquiring the first candidate point with the largest included angle with the y direction from all the first candidate line segments based on the current boundary point on the basis of the previous boundary point as the next boundary point.
As a further improvement of the present application, each boundary point is connected in turn based on the layout to form boundaries of all point cloud data, and thereafter, includes:
judging whether the connecting lines of the boundaries are intersected or not;
if yes, expanding the preset first radius range according to a preset amplitude to form a second preset radius range;
Connecting each current candidate point with the last boundary point to form a current candidate line segment;
acquiring a current candidate point with the largest included angle with the y direction in all current candidate line segments as a next boundary point;
And continuously acquiring the next candidate point with the largest included angle with the y direction in all the next candidate line segments on the basis of the current boundary point as the next boundary point.
As a further improvement of the present application, continuously acquiring, based on the current boundary point, a next candidate point having the largest included angle with the y direction from among all the next candidate line segments as a next boundary point, including:
judging whether the second uniformity of the point cloud data positioned in the current boundary point within the preset second radius range is smaller than or equal to the preset threshold value;
If the second uniformity is smaller than or equal to the preset threshold, acquiring two point cloud data closest to the current boundary point as candidate points of two next boundary points;
Connecting each candidate point of the next boundary point with the previous boundary point to form a current candidate line segment;
judging whether the ratio of a shorter line segment to a longer line segment in the two current candidate line segments is smaller than or equal to the preset ratio;
If yes, selecting a current candidate point corresponding to a shorter line segment in the current candidate line segments as a next boundary point.
In order to achieve the above purpose, the present application further provides the following technical solutions:
A boundary extraction apparatus of point cloud data, the boundary extraction apparatus of point cloud data being applied to the boundary extraction method of point cloud data as described above, the boundary extraction apparatus of point cloud data comprising:
The point cloud data output module is used for inputting all the point cloud data in the layout;
The boundary range determining module is used for determining the boundary range of the layout according to the range covered by all the point cloud data;
The grid establishing and assigning module is used for establishing grids with preset density according to the boundary range and assigning 0 to each sub-grid of the grids;
the point cloud data acquisition and assignment module is used for respectively acquiring the number of the point cloud data of each sub-grid and assigning the sub-grids with the number larger than the preset number to be 1;
The matrix definition and assignment module is used for defining each sub-grid and the adjacent sub-grids as a matrix, and respectively acquiring assignment values of all the sub-grids in each matrix through a first preset algorithm;
The matrix assignment value judging module is used for judging whether the assignment value of each matrix is 0 or not;
the edge matrix extraction module is used for extracting the matrix with the value of 0 as an edge matrix if the matrix with the value of 0 is available;
The edge point set and boundary point acquisition module is used for respectively extracting the edge point sets of each edge matrix and acquiring boundary points of all the edge point sets according to a second preset algorithm;
and the point cloud data boundary generation module is used for sequentially connecting each boundary point based on the layout to form boundaries of all the point cloud data.
In order to achieve the above purpose, the present application further provides the following technical solutions:
an electronic device comprising a processor, a memory coupled to the processor, the memory storing program instructions executable by the processor; and the processor realizes the boundary extraction method of the point cloud data when executing the program instructions stored in the memory.
In order to achieve the above purpose, the present application further provides the following technical solutions:
a storage medium having stored therein program instructions which, when executed by a processor, implement a boundary extraction method capable of implementing point cloud data as described above.
According to the method, grids with preset density are built in a layout through a sliding window algorithm, each sub-grid of the grids is assigned with 0, the number of point cloud data of each sub-grid is respectively obtained, the number of sub-grids with the number larger than the preset number is assigned with 1, matrixes with assigned values of 0 are extracted through the sliding window and serve as edge matrixes, edge point sets of each edge matrix are respectively extracted, boundary points of all the edge point sets are obtained according to a second preset algorithm, and each boundary point is sequentially connected based on the layout to form boundaries of all the point cloud data. According to the application, the efficient extraction of the point cloud data boundary is realized, the points participating in calculation are reduced through the grid division and sliding window algorithm, the time required for extracting the boundary of millions of point cloud data in the actual process is only about six seconds, the calculation efficiency is obviously improved, and the calculation force burden of the algorithm is reduced, so that the processing speed is increased.
Drawings
FIG. 1 is a schematic diagram illustrating steps in a process of an embodiment of a boundary extraction method for point cloud data according to the present application;
FIG. 2 is a schematic diagram of a functional module of an embodiment of a boundary extraction device for point cloud data according to the present application;
FIG. 3 is a schematic diagram of an embodiment of an electronic device of the present application;
FIG. 4 is a schematic diagram illustrating the structure of an embodiment of a storage medium according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," "third," and the like in this disclosure are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "first," "second," and "third" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise. All directional indications (such as up, down, left, right, front, back … …) in the embodiments of the present application are merely used to explain the relative positional relationship, movement, etc. between the components in a particular gesture (as shown in the drawings), and if the particular gesture changes, the directional indication changes accordingly. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
As shown in fig. 1, the present embodiment provides an embodiment of a boundary extraction method of point cloud data, and in the present embodiment, the boundary extraction method includes the steps of:
Step S1, inputting all point cloud data in the layout.
And S2, determining the boundary range of the layout according to the range covered by all the point cloud data.
And S3, establishing grids with preset density according to the boundary range, and assigning 0 to each sub-grid of the grids.
Preferably, the boundary range of the grid is determined, that is, the boundary values of the layout in the X-direction and the Y-direction are determined, and the data is grid-divided by selecting an appropriate grid side length to determine the shape (rank number) of the grid.
Preferably, the smaller the meshing, i.e. the larger the value of the partitional mesh, the fewer the number of edge point sets calculated and vice versa, the appropriate mesh side length can be selected according to the actual need.
And S4, respectively acquiring the number of the point cloud data of each sub-grid, and assigning the sub-grids with the number larger than the preset number as 1.
And S5, defining each sub-grid and adjacent sub-grids as a matrix, and respectively acquiring the assigned values of all the sub-grids in each matrix through a first preset algorithm.
And S6, judging whether the assigned value of each matrix is 0 or not, and if the matrix with the assigned value of 0 exists, executing the step S7.
And S7, extracting a matrix with a value of 0 as an edge matrix.
It should be noted that, the assignment of the grid located at the center position in the edge matrix should be 1 to ensure the accuracy of the subsequent estimation.
And S8, respectively extracting edge point sets of each edge matrix, and acquiring boundary points of all the edge point sets according to a second preset algorithm.
Step S9, sequentially connecting each boundary point based on the layout to form boundaries of all point cloud data.
Further, the step S5 specifically includes the following steps:
In step S51, each sub-grid and eight sub-grids adjacent to each sub-grid are defined as a 3×3 matrix.
Similarly, the assignment of the grid in the center position in the 3×3 matrix must be 1 to ensure the accuracy of the subsequent estimation.
Step S52, judging whether the sub-grids in each 3X 3 matrix are assigned with 0 through a sliding window algorithm, and if no sub-grids are assigned with 0, executing step 53.
At step 53, the 3 x 3 matrix with value 0 without sub-grid is deleted.
Further, the step S8 specifically includes the following steps:
Step S81, the row and column value of each point cloud data in each edge matrix is calculated respectively, and a lattice to be connected is established for each point cloud data according to the Krueskal algorithm.
Step S82, obtaining the minimum spanning tree of the lattice to be communicated according to the Krueskal algorithm.
Step S83, extracting point cloud data in the minimum spanning tree and using the point cloud data as an edge point set.
Step S84, based on the y direction of the grid, acquiring point cloud data with the smallest y value in the edge point set as a first boundary point.
In step S85, point cloud data located in a preset first radius range of the first boundary point is obtained as a first candidate point.
In step S86, each first candidate point is connected to the first boundary point to form a first candidate line segment.
Step S87, the first candidate point with the largest included angle with the y direction in all the first candidate line segments is obtained as the second boundary point.
In step S88, the first candidate point with the largest included angle with the y direction in all the first candidate line segments based on the current boundary point is continuously obtained as the next boundary point based on the previous boundary point.
Preferably, a judgment method of a fixed K value is selected in a preset first radius range, and the judgment method is suitable for a scene with more uniform point cloud data, namely, the judgment method of a next boundary point is that firstly, K nearest candidate points, namely, K points with the smallest distance are selected by taking a previous boundary point as an origin, and the maximum value of the clockwise included angle between the connecting line of the selected K points and the previous point and a Y axis is calculated; when the trend of the connecting line of the upper two boundary points is upward, calculating the angle as the maximum value of the clockwise included angle between the connecting line of the selected K points and the upper point and the negative half axis of the Y axis; otherwise, the front half shaft is the right half shaft.
Further, after step S85, the method further includes the following steps:
Step S851, judging a first uniformity of the point cloud data within a first radius range of the first boundary point preset, and if the first uniformity is less than or equal to a first preset threshold, executing step S852.
In step S852, two point cloud data closest to the first boundary point are acquired as two second candidate points.
In step S853, each of the second candidate points is connected to the first boundary point to form a second candidate line segment.
Step S854, judging whether the ratio of the shorter line segment to the longer line segment in the two second candidate line segments is smaller than or equal to a preset ratio, if the ratio of the shorter line segment to the longer line segment is smaller than or equal to the preset ratio, executing step S855; if the ratio of the shorter line segment to the longer line segment is greater than the preset ratio, step S856 is performed.
In step S855, a second candidate point corresponding to the shorter line segment is selected as the next boundary point.
In step S856, the first candidate point with the largest included angle with the y direction in all the first candidate line segments based on the current boundary point is continuously obtained as the next boundary point based on the previous boundary point.
Preferably, a method for judging the variable K value in the preset first radius range is suitable for a scene with uneven point cloud data, that is, a method for judging the next boundary point is to select the K nearest candidate points, that is, the K points with the smallest distance, by taking the previous boundary point as the origin. Then judging the distance between two nearest points in the K candidate points to obtain a line segment om and a line segment on, and if om/on is less than or equal to 0.8, selecting a point m as a next boundary point; if om/on > 0.8, the above-mentioned fixed K value judging method is adopted.
Preferably, after each boundary point is connected in turn to form the boundary of all point cloud data, whether the end to end of the boundary is connected can be further judged, and if the range is closed, a final boundary point set and a boundary point range can be obtained. If the two boundary points cannot be connected end to end, the search range of K is enlarged (namely, the first preset radius range or the second preset radius range is further enlarged), and the recalculation is started from the second boundary point. If the intersecting condition does not exist, the boundary point can be determined, the next boundary point is determined continuously according to the method until the first boundary point is selected again, and then the closing of the polygon is completed.
Further, after step S9, it includes:
step S10, judging whether the connecting lines of the boundary are intersected, and if so, executing step S11.
Step S11, expanding the preset first radius range according to the preset amplitude to form a second preset radius range.
Step S12, each current candidate point is respectively connected with the last boundary point to form a current candidate line segment.
And S13, acquiring the current candidate point with the largest included angle with the y direction in all the current candidate line segments as the next boundary point.
Step S14, continuously acquiring the next candidate point with the largest included angle with the y direction in all the next candidate line segments as the next boundary point based on the current boundary point.
Preferably, if there is an intersection between the connecting lines of the boundary points, the judgment is performed by selecting the second closest candidate point as the boundary point, and if none of the K candidate points is satisfied, the search range of K is expanded to be recalculated from the second boundary point (i.e., the first preset radius range is expanded to the second preset radius range or more). If the intersecting condition does not exist, the boundary point can be determined, the next boundary point is determined continuously according to the method until the first boundary point is selected again, and then the closing of the polygon is completed.
Further, the step S14 specifically includes the following steps:
step S141, judging whether the second uniformity of the point cloud data within the preset second radius range of the current boundary point is smaller than or equal to a preset threshold value, if the second uniformity is smaller than or equal to the preset threshold value, executing step S142.
In step S142, two point cloud data closest to the current boundary point are acquired as candidate points of two next boundary points.
In step S143, each candidate point of the next boundary points is connected to the previous boundary point to form a current candidate line segment.
Step S144, judging whether the ratio of the shorter line segment to the longer line segment in the two current candidate line segments is smaller than or equal to a preset ratio, if the ratio of the shorter line segment to the longer line segment in the two current candidate line segments is smaller than or equal to the preset ratio, executing step S145.
Step S145, selecting the current candidate point corresponding to the shorter line segment of the current candidate line segments as the next boundary point.
According to the embodiment, grids with preset density are built in a layout through a sliding window algorithm, each sub-grid of the grids is assigned with 0, the number of point cloud data of each sub-grid is respectively obtained, the number of sub-grids with the number larger than the preset number is assigned with 1, matrixes with assigned values of 0 are extracted through the sliding window and serve as edge matrixes, edge point sets of each edge matrix are respectively extracted, boundary points of all the edge point sets are obtained according to a second preset algorithm, and each boundary point is sequentially connected based on the layout to form boundaries of all the point cloud data. According to the application, the efficient extraction of the point cloud data boundary is realized, the points involved in calculation are reduced through the grid division and sliding window algorithm, the time required for extracting the boundary of millions of point cloud data in the actual process is only about six seconds, the calculation efficiency is obviously improved, the calculation force burden of the algorithm is reduced, the processing speed is further increased, and the accuracy of boundary calculation is ensured by applying the K-neighbor algorithm (namely, the first preset radius range and the second preset radius range).
As shown in fig. 2, this embodiment also provides an embodiment of a boundary extraction apparatus for point cloud data, where the boundary extraction apparatus for point cloud data is applied to the boundary extraction method for point cloud data in the foregoing embodiment, and the boundary extraction apparatus for point cloud data includes a point cloud data output module 1, a boundary range determination module 2, a mesh creation and assignment module 3, a point cloud data acquisition and assignment module 4, a matrix definition and assignment module 5, a matrix assignment value judgment module 6, an edge matrix extraction module 7, an edge point set and boundary point acquisition module 8, and a point cloud data boundary generation module 9 that are sequentially connected or interconnected.
The point cloud data output module 1 is used for inputting all point cloud data in the layout; the boundary range determining module 2 is used for determining the boundary range of the layout according to the range covered by all the point cloud data; the grid establishing and assigning module 3 is used for establishing grids with preset density according to the boundary range and assigning 0 to each sub-grid of the grids; the point cloud data acquisition and assignment module 4 is used for respectively acquiring the number of the point cloud data of each sub-grid and assigning the sub-grids with the number larger than the preset number to be 1; the matrix definition and assignment module 5 is used for defining each sub-grid and adjacent sub-grids as a matrix, and respectively acquiring assignment values of all the sub-grids in each matrix through a first preset algorithm; the matrix assignment value judging module 6 is used for judging whether an assignment value in each matrix is 0 or not respectively; the edge matrix extraction module 7 is used for extracting a matrix with a value of 0 as an edge matrix if the matrix with the value of 0 is available; the edge point set and boundary point acquisition module 8 is used for respectively extracting edge point sets of each edge matrix and acquiring boundary points of all the edge point sets according to a second preset algorithm; the point cloud data boundary generation module 9 is configured to sequentially connect each boundary point based on the layout to form boundaries of all the point cloud data.
Further, the matrix definition and assignment module comprises a first matrix definition and assignment sub-module, a second matrix definition and assignment sub-module and a third matrix definition and assignment sub-module which are connected in sequence or mutually connected.
Wherein the first matrix definition and assignment sub-module is used for defining each sub-grid and eight sub-grids adjacent to each sub-grid as a 3×3 matrix; the second matrix definition and assignment submodule is used for judging whether the assignment of the subgrid in each 3 multiplied by 3 matrix is 0 through a sliding window algorithm; the third matrix definition and assignment sub-module is configured to delete the 3×3 matrix with no sub-grid assigned 0 if no sub-grid is assigned 0.
Further, the edge point set and boundary point acquisition module comprises a first edge point set and boundary point acquisition sub-module, a second edge point set and boundary point acquisition sub-module, a third edge point set and boundary point acquisition sub-module, a fourth edge point set and boundary point acquisition sub-module, a fifth edge point set and boundary point acquisition sub-module, a sixth edge point set and boundary point acquisition sub-module, a seventh edge point set and boundary point acquisition sub-module, and a eighth edge point set and boundary point acquisition sub-module which are sequentially connected or interconnected.
The first edge point set and boundary point acquisition submodule is used for respectively calculating the row and column value of each point cloud data in each edge matrix and establishing a lattice to be communicated for each point cloud data according to a Krueskal algorithm; the second edge point set and boundary point acquisition submodule is used for acquiring a minimum spanning tree of the lattice to be communicated according to the Krueskal algorithm; the third edge point set and boundary point acquisition submodule is used for extracting point cloud data in the minimum spanning tree and taking the point cloud data as an edge point set; the fourth edge point set and boundary point acquisition submodule is used for acquiring point cloud data with the smallest y value in the edge point set as a first boundary point based on the y direction of the grid; the fifth edge point set and boundary point acquisition sub-module is used for acquiring point cloud data positioned in a first radius range preset by the first boundary point as a first candidate point; the sixth edge point set and boundary point acquisition submodule is used for connecting each first candidate point with a first boundary point respectively to form a first candidate line segment; the seventh boundary point set and boundary point acquisition submodule is used for acquiring a first candidate point with the largest included angle with the y direction in all the first candidate line segments as a second boundary point; the eighth boundary point set and boundary point acquisition submodule is used for continuously acquiring a first candidate point with the largest included angle with the y direction in all first candidate line segments based on the current boundary point as the next boundary point based on the previous boundary point.
Further, the edge point set and boundary point acquisition module further includes a ninth edge point set and boundary point acquisition sub-module, a tenth edge point set and boundary point acquisition sub-module, an eleventh edge point set and boundary point acquisition sub-module, a twelfth edge point set and boundary point acquisition sub-module, a thirteenth edge point set and boundary point acquisition sub-module, and a fourteenth edge point set and boundary point acquisition sub-module which are sequentially connected or interconnected.
The ninth edge point set and boundary point acquisition submodule is used for judging first uniformity of point cloud data in a first radius range preset by a first boundary point; the tenth edge point set and boundary point acquisition submodule is used for acquiring two point cloud data closest to the first boundary point as two second candidate points if the first uniformity is smaller than or equal to a first preset threshold value; the eleventh edge point set and boundary point acquisition submodule is used for connecting each second candidate point with the first boundary point respectively to form a second candidate line segment; the twelfth edge point set and boundary point acquisition submodule is used for judging whether the ratio of a shorter line segment to a longer line segment in the two second candidate line segments is smaller than or equal to a preset ratio; the thirteenth edge point set and boundary point obtaining submodule is used for selecting a second candidate point corresponding to the shorter line segment as a next boundary point if the ratio of the shorter line segment to the longer line segment is smaller than or equal to a preset ratio; the fourteenth edge point set and boundary point obtaining submodule is used for continuously obtaining a first candidate point with the largest included angle with the y direction in all first candidate line segments based on the current boundary point as a next boundary point based on the previous boundary point if the ratio of the shorter line segment to the longer line segment is larger than a preset ratio.
Further, the boundary extraction device of the point cloud data further comprises a boundary connecting line judging module, a preset radius range adjusting module, a current candidate line segment connecting module, a boundary point obtaining module and a boundary point continuous obtaining module which are connected in sequence or mutually connected.
The boundary connecting wire judging module is used for judging whether connecting wires of the boundary are intersected or not; the preset radius range adjusting module is used for expanding the preset first radius range according to the preset amplitude to form a second preset radius range if the connecting lines of the boundaries are intersected; the current candidate line segment connecting module is used for connecting each current candidate point with the last boundary point to form a current candidate line segment; the boundary point acquisition module is used for acquiring the current candidate point with the largest included angle with the y direction in all the current candidate line segments as the next boundary point; the boundary point continuous acquisition module is used for continuously acquiring the next candidate point with the largest included angle with the y direction in all the next candidate line segments as the next boundary point based on the current boundary point.
Further, the boundary point continuous acquisition module specifically includes a first boundary point continuous acquisition sub-module, a second boundary point continuous acquisition sub-module, a third boundary point continuous acquisition sub-module, a fourth boundary point continuous acquisition sub-module, and a fifth boundary point continuous acquisition sub-module which are sequentially connected or interconnected.
The first boundary point continuous acquisition sub-module is used for judging whether second uniformity of point cloud data in a preset second radius range of the current boundary point is smaller than or equal to a preset threshold value; the second boundary point continuous acquisition sub-module is used for acquiring two point cloud data closest to the current boundary point as candidate points of two next boundary points if the second uniformity is smaller than or equal to a preset threshold value; the third boundary point continuous acquisition sub-module is used for connecting each candidate point of the next boundary point with the last boundary point respectively to form a current candidate line segment; the fourth boundary point continuous acquisition submodule is used for judging whether the ratio of a shorter line segment to a longer line segment in the two current candidate line segments is smaller than or equal to a preset ratio; and the fifth boundary point continuous acquisition sub-module is used for selecting the current candidate point corresponding to the shorter line segment in the current candidate line segments as the next boundary point if the ratio of the shorter line segment to the longer line segment in the two current candidate line segments is smaller than or equal to a preset ratio.
According to the embodiment, grids with preset density are built in a layout through a sliding window algorithm, each sub-grid of the grids is assigned with 0, the number of point cloud data of each sub-grid is respectively obtained, the number of sub-grids with the number larger than the preset number is assigned with 1, matrixes with assigned values of 0 are extracted through the sliding window and serve as edge matrixes, edge point sets of each edge matrix are respectively extracted, boundary points of all the edge point sets are obtained according to a second preset algorithm, and each boundary point is sequentially connected based on the layout to form boundaries of all the point cloud data. According to the application, the efficient extraction of the point cloud data boundary is realized, the points involved in calculation are reduced through the grid division and sliding window algorithm, the time required for extracting the boundary of millions of point cloud data in the actual process is only about six seconds, the calculation efficiency is obviously improved, the calculation force burden of the algorithm is reduced, the processing speed is further increased, and the accuracy of boundary calculation is ensured by applying the K-neighbor algorithm (namely, the first preset radius range and the second preset radius range).
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 3, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.
The memory 102 stores program instructions for implementing the fault detection method of the oil-immersed transformer according to any of the above embodiments.
The processor 101 is configured to execute program instructions stored in the memory 102 to perform fault detection of the oil-immersed transformer.
The processor 101 may also be referred to as a CPU (Central Processing Unit ). The processor 101 may be an integrated circuit chip with signal processing capabilities. Processor 101 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Further, fig. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application, referring to fig. 4, where the storage medium 11 according to an embodiment of the present application stores a program instruction 111 capable of implementing all the methods described above, where the program instruction 111 may be stored in the storage medium in the form of a software product, and includes several instructions for making a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes, or a terminal device such as a computer, a server, a mobile phone, a tablet, or the like.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. The foregoing is only the embodiments of the present application, and the patent scope of the application is not limited thereto, but is also covered by the patent protection scope of the application, as long as the equivalent structure or equivalent flow changes made by the description and the drawings of the application or the direct or indirect application in other related technical fields are adopted.
Claims (8)
1. A boundary extraction method of point cloud data, the boundary extraction method comprising:
Inputting all point cloud data in the layout;
Determining the boundary range of the layout according to the range covered by all the point cloud data;
establishing grids with preset density according to the boundary range, and assigning 0 to each sub-grid of the grids;
Respectively acquiring the number of the point cloud data of each sub-grid, and assigning the sub-grids with the number larger than the preset number as 1;
defining each sub-grid and adjacent sub-grids as a matrix, and respectively acquiring assigned values of all the sub-grids in each matrix through a first preset algorithm;
Judging whether the assigned value of each matrix is 0or not;
if so, extracting a matrix with a value of 0 and taking the matrix as an edge matrix;
respectively extracting edge point sets of point cloud data in each edge matrix, and acquiring boundary points of all the edge point sets according to a second preset algorithm;
sequentially connecting each boundary point based on the layout to form boundaries of all point cloud data;
Defining each sub-grid and adjacent sub-grids as a matrix, and respectively acquiring the assigned values of all the sub-grids in each matrix through a first preset algorithm, wherein the method comprises the following steps:
Defining each sub-grid and eight sub-grids adjacent to each sub-grid as a 3 x 3 matrix;
judging whether the assignment of the subgrid in each 3 multiplied by 3 matrix is 0 through a sliding window algorithm;
if not, deleting the 3 multiplied by 3 matrix with the value of 0 and without the submesh;
Respectively extracting edge point sets of point cloud data in each edge matrix, and acquiring boundary points of all the edge point sets according to a second preset algorithm, wherein the method comprises the following steps:
respectively calculating a row-column value of each point cloud data in each edge matrix and establishing a lattice to be communicated for each point cloud data according to a Krueskal algorithm;
Obtaining the minimum spanning tree of the lattice to be communicated according to the Krueskal algorithm;
extracting point cloud data in the minimum spanning tree and taking the point cloud data as the edge point set;
Acquiring point cloud data with the smallest y value in the edge point set as a first boundary point based on the y direction of the grid;
Acquiring point cloud data in a first radius range preset by the first boundary point as a first candidate point;
Connecting each first candidate point with the first boundary point to form a first candidate line segment;
Acquiring first candidate points with the largest included angles with the y direction in all the first candidate line segments as second boundary points;
and continuously acquiring a first candidate point with the largest included angle with the y direction in all first candidate line segments based on the current boundary point as the next boundary point on the basis of the previous boundary point.
2. The boundary extraction method of point cloud data according to claim 1, wherein acquiring point cloud data located within a preset first radius range of the first boundary point as a first candidate point, and thereafter, comprises:
judging first uniformity of point cloud data in the preset first radius range of the first boundary point;
If the first uniformity is smaller than or equal to a first preset threshold value, acquiring two point cloud data closest to the first boundary point as two second candidate points;
connecting each second candidate point with the first boundary point to form a second candidate line segment;
judging whether the ratio of a shorter line segment to a longer line segment in the two second candidate line segments is smaller than or equal to a preset ratio;
If yes, selecting a second candidate point corresponding to the shorter line segment as the next boundary point.
3. The boundary extraction method of point cloud data according to claim 2, wherein determining whether a ratio of a shorter line segment to a longer line segment of the two second candidate line segments is equal to or smaller than a preset ratio, comprises:
If not, continuously acquiring the first candidate point with the largest included angle with the y direction from all the first candidate line segments based on the current boundary point on the basis of the previous boundary point as the next boundary point.
4. The boundary extraction method of point cloud data according to claim 2, wherein each boundary point is connected in turn based on the layout to form boundaries of all point cloud data, and thereafter, comprising:
judging whether the connecting lines of the boundaries are intersected or not;
if yes, expanding the preset first radius range according to a preset amplitude to form a second preset radius range;
Connecting each current candidate point with the last boundary point to form a current candidate line segment;
acquiring a current candidate point with the largest included angle with the y direction in all current candidate line segments as a next boundary point;
And continuously acquiring the next candidate point with the largest included angle with the y direction in all the next candidate line segments on the basis of the current boundary point as the next boundary point.
5. The boundary extraction method of point cloud data according to claim 4, wherein continuously acquiring, based on a current boundary point, a next candidate point having a largest included angle with the y direction among all the next candidate line segments as a next boundary point, comprises:
judging whether the second uniformity of the point cloud data positioned in the second preset radius range of the current boundary point is smaller than or equal to the preset threshold value;
If the second uniformity is smaller than or equal to the preset threshold, acquiring two point cloud data closest to the current boundary point as candidate points of two next boundary points;
Connecting each candidate point of the next boundary point with the previous boundary point to form a current candidate line segment;
judging whether the ratio of a shorter line segment to a longer line segment in the two current candidate line segments is smaller than or equal to the preset ratio;
If yes, selecting a current candidate point corresponding to a shorter line segment in the current candidate line segments as a next boundary point.
6. A boundary extraction apparatus of point cloud data, the boundary extraction apparatus of point cloud data being applied to the boundary extraction method of point cloud data according to one of claims 1 to 5, characterized in that the boundary extraction apparatus of point cloud data comprises:
The point cloud data output module is used for inputting all the point cloud data in the layout;
The boundary range determining module is used for determining the boundary range of the layout according to the range covered by all the point cloud data;
The grid establishing and assigning module is used for establishing grids with preset density according to the boundary range and assigning 0 to each sub-grid of the grids;
the point cloud data acquisition and assignment module is used for respectively acquiring the number of the point cloud data of each sub-grid and assigning the sub-grids with the number larger than the preset number to be 1;
The matrix definition and assignment module is used for defining each sub-grid and the adjacent sub-grids as a matrix, and respectively acquiring assignment values of all the sub-grids in each matrix through a first preset algorithm;
the matrix assignment value judging module is used for judging whether an assignment value is 0 in each matrix or not respectively;
the edge matrix extraction module is used for extracting the matrix with the value of 0 as an edge matrix if the matrix with the value of 0 is available;
The edge point set and boundary point acquisition module is used for respectively extracting the edge point sets of each edge matrix and acquiring boundary points of all the edge point sets according to a second preset algorithm;
The point cloud data boundary generation module is used for sequentially connecting each boundary point based on the layout to form boundaries of all point cloud data;
the matrix definition and assignment module comprises a first matrix definition and assignment sub-module, a second matrix definition and assignment sub-module and a third matrix definition and assignment sub-module which are connected in sequence or mutually connected;
Wherein the first matrix definition and assignment sub-module is used for defining each sub-grid and eight sub-grids adjacent to each sub-grid as a 3×3 matrix; the second matrix definition and assignment submodule is used for judging whether the assignment of the subgrid in each 3 multiplied by 3 matrix is 0 through a sliding window algorithm; the third matrix definition and assignment sub-module is used for deleting the 3 multiplied by 3 matrix with no sub-grid with the assignment of 0 if the assignment of no sub-grid is 0;
the edge point set and boundary point acquisition module comprises a first edge point set and boundary point acquisition sub-module, a second edge point set and boundary point acquisition sub-module, a third edge point set and boundary point acquisition sub-module, a fourth edge point set and boundary point acquisition sub-module, a fifth edge point set and boundary point acquisition sub-module, a sixth edge point set and boundary point acquisition sub-module, a seventh edge point set and boundary point acquisition sub-module, and a eighth edge point set and boundary point acquisition sub-module which are connected in sequence or mutually;
The first edge point set and boundary point acquisition submodule is used for respectively calculating the row and column value of each point cloud data in each edge matrix and establishing a lattice to be communicated for each point cloud data according to a Krueskal algorithm; the second edge point set and boundary point acquisition submodule is used for acquiring a minimum spanning tree of the lattice to be communicated according to the Krueskal algorithm; the third edge point set and boundary point acquisition submodule is used for extracting point cloud data in the minimum spanning tree and taking the point cloud data as an edge point set; the fourth edge point set and boundary point acquisition submodule is used for acquiring point cloud data with the smallest y value in the edge point set as a first boundary point based on the y direction of the grid; the fifth edge point set and boundary point acquisition sub-module is used for acquiring point cloud data positioned in a first radius range preset by the first boundary point as a first candidate point; the sixth edge point set and boundary point acquisition submodule is used for connecting each first candidate point with a first boundary point respectively to form a first candidate line segment; the seventh boundary point set and boundary point acquisition submodule is used for acquiring a first candidate point with the largest included angle with the y direction in all the first candidate line segments as a second boundary point; the eighth boundary point set and boundary point acquisition submodule is used for continuously acquiring a first candidate point with the largest included angle with the y direction in all first candidate line segments based on the current boundary point as the next boundary point based on the previous boundary point.
7. An electronic device comprising a processor, and a memory coupled to the processor, the memory storing program instructions executable by the processor; the processor, when executing the program instructions stored in the memory, implements a method for boundary extraction of point cloud data according to any one of claims 1 to 5.
8. A storage medium having stored therein program instructions which, when executed by a processor, implement a boundary extraction method capable of implementing a point cloud data according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310552077.9A CN116503434B (en) | 2023-05-15 | 2023-05-15 | Boundary extraction method, device and equipment of point cloud data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310552077.9A CN116503434B (en) | 2023-05-15 | 2023-05-15 | Boundary extraction method, device and equipment of point cloud data and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116503434A CN116503434A (en) | 2023-07-28 |
| CN116503434B true CN116503434B (en) | 2024-07-16 |
Family
ID=87320131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310552077.9A Active CN116503434B (en) | 2023-05-15 | 2023-05-15 | Boundary extraction method, device and equipment of point cloud data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503434B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927234A (en) * | 2021-02-25 | 2021-06-08 | 中国工商银行股份有限公司 | Point cloud semantic segmentation method and device, electronic equipment and readable storage medium |
| CN114170401A (en) * | 2021-12-10 | 2022-03-11 | 北京超星未来科技有限公司 | Point cloud data sampling method and device, computer equipment and readable storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113050993A (en) * | 2019-12-27 | 2021-06-29 | 中兴通讯股份有限公司 | Laser radar-based detection method and device and computer-readable storage medium |
| CN113806464A (en) * | 2021-09-18 | 2021-12-17 | 北京京东乾石科技有限公司 | Road tooth determining method, device, equipment and storage medium |
| CN114581619A (en) * | 2022-02-25 | 2022-06-03 | 浙江工业大学 | Coal bunker modeling method based on three-dimensional positioning and two-dimensional mapping |
| CN115327539A (en) * | 2022-07-19 | 2022-11-11 | 际络科技(上海)有限公司 | Road guardrail detection method and device |
| CN115690138A (en) * | 2022-10-18 | 2023-02-03 | 武汉大学 | Road boundary extraction and vectorization method fusing vehicle-mounted image and point cloud |
-
2023
- 2023-05-15 CN CN202310552077.9A patent/CN116503434B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927234A (en) * | 2021-02-25 | 2021-06-08 | 中国工商银行股份有限公司 | Point cloud semantic segmentation method and device, electronic equipment and readable storage medium |
| CN114170401A (en) * | 2021-12-10 | 2022-03-11 | 北京超星未来科技有限公司 | Point cloud data sampling method and device, computer equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116503434A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112233240B (en) | Three-dimensional vector data slicing method and device of three-dimensional vector map and electronic equipment | |
| CN111831660B (en) | Method and device for evaluating metric space division mode, computer equipment and storage medium | |
| CN110544298B (en) | Substation modeling method, device, computer equipment and storage medium | |
| CN110544308B (en) | Transformer substation modeling method and device, computer equipment and storage medium | |
| CN110033519A (en) | Three-dimensional modeling method, device, system and storage medium based on Implicitly function | |
| CN111090712A (en) | Data processing method, device and equipment and computer storage medium | |
| CN108961294A (en) | A kind of dividing method and device of three-dimensional point cloud | |
| CN113487523B (en) | Method and device for optimizing graph contour, computer equipment and storage medium | |
| Papagiannopoulos et al. | How to teach neural networks to mesh: Application on 2-D simplicial contours | |
| CN111707279A (en) | Matching evaluation method, medium, terminal and device of laser point cloud and map | |
| CN108364331A (en) | A kind of isopleth generation method, system and storage medium | |
| KR20030050308A (en) | Mesh simplification method by non-uniformed spatial subdivision | |
| CN115098717A (en) | Three-dimensional model retrieval method and device, electronic equipment and storage medium | |
| CN116503434B (en) | Boundary extraction method, device and equipment of point cloud data and storage medium | |
| CN115481268A (en) | Parallel line wall data identification method, device, equipment and storage medium | |
| CN115792900A (en) | Deformation detection method and system for geological sensitive area of power transmission channel | |
| CN110349265B (en) | Tetrahedral topological mesh generation method and electronic equipment | |
| CN115049997A (en) | Method and device for generating edge lane line, electronic device and storage medium | |
| JP7056452B2 (en) | Simulation equipment, simulation method and simulation program | |
| CN113920079A (en) | Difficult sample mining method, system, terminal and storage medium | |
| CN117407727B (en) | Vector similarity determining method and vector searching method | |
| CN115830269B (en) | Tunnel point cloud normal direction adjustment method, device, equipment and readable access medium | |
| CN117934573B (en) | Point cloud data registration method and device and electronic equipment | |
| CN112434177B (en) | Three-dimensional model retrieval method and device, electronic equipment and storage medium | |
| CN112950706B (en) | Mobile equipment positioning data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |