CN113192172B - Airborne LiDAR ground point cloud simplification method - Google Patents
Airborne LiDAR ground point cloud simplification method Download PDFInfo
- Publication number
- CN113192172B CN113192172B CN202110599859.9A CN202110599859A CN113192172B CN 113192172 B CN113192172 B CN 113192172B CN 202110599859 A CN202110599859 A CN 202110599859A CN 113192172 B CN113192172 B CN 113192172B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- ground point
- clustering
- simplification
- cluster
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000005070 sampling Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000001788 irregular Effects 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 description 7
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000903 blocking effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Graphics (AREA)
- Image Analysis (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses an airborne LiDAR ground point cloud simplification method, which comprises the following steps: s1, preprocessing the original LiDAR ground point cloud data; s2, selecting m terrain feature factors based on the original LiDAR ground point cloud data; s3, introducing a half-variation function, and determining the spatial autocorrelation range of each topographic feature factor based on the preprocessed original LiDAR ground point cloud data; s4, carrying out spatial autocorrelation hierarchical clustering based on spatial autocorrelation ranges of various topographic characteristic factors to obtain corresponding clustering results; and S5, selecting the characteristic points according to the clustering result to further obtain a point cloud simplification result. According to the method, a clustering idea is introduced, the rationality of the spatial distribution of the feature points and the terrain similarity feature among the ground points are considered in the simplification process, and finally the high-precision DEM is constructed by using less point clouds, so that a new idea is provided for the simplification of the ground point clouds.
Description
Technical Field
The invention belongs to the technical field of point cloud simplification, and particularly relates to an airborne LiDAR ground point cloud simplification method based on a spatial autocorrelation hierarchical clustering algorithm.
Background
An airborne laser radar (LiDAR) can rapidly acquire large-area, high-density And high-precision three-dimensional point cloud in various complex environments, And is one of important technical means for constructing a high-precision Digital Elevation Model (DEM) at present. However, these high-precision three-dimensional point cloud models contain a large amount of redundant data, which always affects the efficiency of subsequent data processing. Therefore, massive LiDAR point cloud data needs to be simplified on the premise of keeping basic topographic features of the original ground point cloud.
Existing LiDAR ground point cloud simplification methods can be broadly divided into two methods based on different terrain feature factors. The first is a simplification method based on a single characteristic factor, which sets the single characteristic factor to describe the topographic features of the point cloud, thereby realizing the simplification of the point cloud. Most of the methods can greatly retain the characteristics of the original model; the second method is a simplification method based on multiple characteristic factors, and the method sets multiple characteristic factors, such as curvature, curvature local entropy, gradient and the like, obtains the terrain complexity of a local area by comprehensively considering the multiple characteristic factors, and sets different characteristic point sampling rules according to different terrain complexities, thereby realizing the simplification of point cloud.
However, the two methods usually use terrain feature factors such as elevation difference, curvature, normal vector, gradient and information entropy as criteria, and subjectively set up the selection threshold of the point cloud and make a sampling rule to realize point cloud simplification based on the precision requirement specified by priori knowledge or a specific scale DEM. The terrain adaptability is low.
Disclosure of Invention
Aiming at the defects in the prior art, the airborne LiDAR ground point cloud simplification method provided by the invention solves the problem of data redundancy existing when the DEM is constructed by the existing three-dimensional point cloud data.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that: an airborne LiDAR ground point cloud simplification method, comprising the steps of:
s1, preprocessing the original LiDAR ground point cloud data;
s2, selecting m terrain feature factors based on the original LiDAR ground point cloud data;
s3, introducing a half-variation function, and determining the spatial autocorrelation range of each topographic feature factor based on the preprocessed original LiDAR ground point cloud data;
s4, carrying out spatial autocorrelation hierarchical clustering based on spatial autocorrelation ranges of all topographic feature factors to obtain corresponding clustering results;
and S5, selecting the characteristic points according to the clustering result to further obtain a point cloud simplification result.
Further, in the step S1, the preprocessing method specifically includes:
a1, calculating all points in the raw LiDAR ground point cloud data to each initial clustering center CiThe Euclidean distance of;
wherein, a subscript i is 1, 2.., K, which is a serial number of a cluster obtained by clustering;
a2, dividing each original LiDAR ground point cloud data into the nearest clusters according to the calculated Euclidean distance until the original LiDAR ground point cloud data are clustered to obtain K clusters, and finishing the preprocessing.
The beneficial effects of the above further scheme are: the original data are clustered into K clusters by using a K-mean + + algorithm so as to achieve the purpose of region blocking, thereby reducing the search range for carrying out spatial autocorrelation range analysis.
Further, the step S2 is specifically:
s21, organizing the original LiDAR ground point cloud data by adopting an irregular triangulation network;
s22, calculating a Spearman correlation coefficient | R | among all terrain feature factors in an irregular triangular network of the tissue;
s23, selecting m terrain feature factors according to the calculated Spearman correlation coefficient | R |.
The beneficial effects of the above further scheme are: and selecting a plurality of effective, independent and relatively comprehensive terrain characteristic factors, thereby being beneficial to LiDAR ground point cloud clustering.
Further, the step S3 is specifically:
s31, constructing a corresponding semi-variation function for each terrain feature factor;
wherein the half-variogram y (h) is:
wherein y (h) is a variance value of the regional variation, h is a step pitch after space, Z (x) and Z (x + h) are variable values of the regionalized variable at spatial positions x and x + h, respectively, and E [ · ] is an expectation function;
s32, setting a half variation function value as a half of the maximum distance of the research area, namely;
in the formula, MaxDis is the maximum distance of a research area, lag is the step length, m is the grouping number under the step length, and floor is a downward integer;
s33, fitting a half-variation function curve by using a spherical model to determine the spatial autocorrelation range of each topographic characteristic factor;
the limiting conditions when determining the spatial autocorrelation range are as follows:
the beneficial effects of the above further scheme are: the variation function is set to be half the maximum distance in the study area so that the variation function is meaningful, and a spherical model is used to fit a half-variation function curve to determine the variation range value.
Further, the step S4 is specifically:
and taking the minimum value of the spatial autocorrelation range corresponding to the terrain characteristic factors in the original LiDAR ground point cloud data of each cluster as a clustering termination threshold value, and performing hierarchical clustering on each cluster respectively to obtain a clustering result.
The beneficial effects of the above further scheme are: based on spatial autocorrelation hierarchical clustering, a clustering result which is close in space and has certain terrain feature similarity, namely a clustering result with low terrain complexity is obtained.
Further, the step S5 specifically includes the following sub-steps:
s51, determining the corresponding relation between each cluster in the clustering result of the SACHCA algorithm and each cluster obtained by preprocessing;
s52, taking each cluster in the clustering result of the SACHCA algorithm as an object, and calculating the average slope AvgSlo of each cluster and the average slope TavgSlo of the corresponding preprocessed cluster;
and S53, sampling the feature points according to the average gradient calculation result, and selecting the feature points in all clusters in the clustering result of the SACHCA algorithm as a point cloud simplification result.
Further, in step S53, when sampling is performed according to the average gradient calculation result, the sampling is performed according to the following principle:
a. if the AvgSlo is larger than TavgSlo, keeping the point with the maximum elevation and the minimum elevation of the current cluster as a characteristic point;
b. if AvgSlo < TavgSlo, the point of the current cluster closest to the centroid is reserved as the feature point.
The beneficial effects of the above further scheme are: the complexity of the topographic surface features is quantitatively described, so that the similarity of ground points on non-space elements can be better balanced in the point cloud simplification process.
The invention has the beneficial effects that:
the method can complete large-scale simplification of mass point cloud data while ensuring high simplification precision, reduces a large amount of redundant data contained in a high-precision three-dimensional point cloud model, realizes the construction of high-precision EDM by using less point clouds on the premise of keeping the basic topographic characteristics of the original ground point cloud, and provides an effective and reliable new method for the analysis and processing of EDM in actual engineering.
Drawings
FIG. 1 is a flow chart of a simplified method for airborne LiDAR ground point cloud provided by the present invention.
FIG. 2 is a diagram illustrating the results of two sets of experimental data preprocessing performed according to an embodiment of the present invention.
FIG. 3 is a schematic diagram of TIN model I of the terrain of the experimental area 1 in the embodiment of the invention.
Fig. 4 is a schematic diagram of a spatial distribution i of sampling points in the experimental area 1 according to the embodiment of the present invention.
Fig. 5 is a schematic diagram of a TIN model ii of the terrain of the experimental area 2 in the embodiment of the present invention.
Fig. 6 is a schematic diagram of spatial distribution ii of sampling points in the experimental area 2 according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
Example 1:
as shown in FIG. 1, an airborne LiDAR ground point cloud simplification method includes the steps of:
s1, preprocessing the original LiDAR ground point cloud data;
s2, selecting m terrain feature factors based on the original LiDAR ground point cloud data;
s3, introducing a half-variation function, and determining the spatial autocorrelation range of each topographic feature factor based on the preprocessed original LiDAR ground point cloud data;
s4, carrying out spatial autocorrelation hierarchical clustering based on spatial autocorrelation ranges of various topographic characteristic factors to obtain corresponding clustering results;
and S5, selecting the characteristic points according to the clustering result to further obtain a point cloud simplification result.
In step S1 of this embodiment, the method for performing the preprocessing specifically includes:
a1, calculating all points in the raw LiDAR ground point cloud data to each initial clustering center CiThe Euclidean distance of;
wherein, a subscript i is 1, 2.., K, which is a serial number of a cluster obtained by clustering;
a2, dividing each original LiDAR ground point cloud data into the nearest clusters according to the calculated Euclidean distance until the original LiDAR ground point cloud data are clustered to obtain K clusters, and finishing the preprocessing.
In the invention, the point cloud data is preprocessed by clustering original data into K clusters by using a K-Mean + + algorithm so as to achieve the aim of region blocking, thereby reducing the search range for carrying out spatial autocorrelation range analysis.
Step S2 of this embodiment specifically includes:
s21, organizing the original LiDAR ground point cloud data by using Irregular triangulation Network (TIN);
s22, calculating a Spearman correlation coefficient | R | among all terrain feature factors in an irregular triangular network of the tissue;
s23, selecting m terrain feature factors according to the calculated Spearman correlation coefficient | R |.
Specifically, if | R | < 0.3 indicates that the correlation among the terrain feature factors is weak or does not have correlation, m effective, independent and relatively comprehensive terrain feature factors are selected so as to carry out the subsequent LiDAR ground point cloud distance.
Step S3 of this embodiment specifically includes:
s31, constructing a corresponding semi-variation function for each terrain feature factor;
wherein the half-variogram y (h) is:
wherein y (h) is a variance value of the regional variation, h is a step pitch after space, Z (x) and Z (x + h) are variable values of the regionalized variable at spatial positions x and x + h, respectively, and E [ · ] is an expectation function;
s32, setting a half variation function value as a half of the maximum distance of the research area, namely;
in the formula, MaxDis is the maximum distance of a research area, lag is the step length, m is the grouping number under the step length, and floor is a downward integer;
s33, fitting a half-variation function curve by using a spherical model to determine the spatial autocorrelation range of each topographic characteristic factor;
the limiting conditions when determining the spatial autocorrelation range are as follows:
in the above process, half of the maximum distance of the variation function in the study area is set so that the variation function is meaningful, and the variation value is determined by fitting a half variation function curve using a spherical model.
Step S4 of this embodiment specifically includes:
and taking the minimum value of the spatial autocorrelation range corresponding to the terrain characteristic factors in the original LiDAR ground point cloud data of each cluster as a clustering termination threshold value, and performing hierarchical clustering on each cluster respectively to obtain a clustering result.
Wherein, the clustering result is obtained by a hierarchical clustering algorithm (SAHCA) based on spatial autocorrelation.
Based on spatial autocorrelation hierarchical clustering, a clustering result which is close in space and has certain terrain feature similarity, namely a clustering result with low terrain complexity is obtained.
Step S5 of this embodiment specifically includes:
s51, determining the corresponding relation between each cluster in the clustering result of the SACHCA algorithm and each cluster obtained by preprocessing;
s52, taking each cluster in the clustering result of the SACHCA algorithm as an object, and calculating the average slope AvgSlo of each cluster and the average slope TavgSlo of the corresponding preprocessed cluster;
and S53, sampling the feature points according to the average gradient calculation result, and selecting the feature points in all clusters in the clustering result of the SACHCA algorithm as a point cloud simplification result.
Specifically, in step S53, when sampling is performed based on the average gradient calculation result, the sampling is performed according to the following principle:
a. if the AvgSlo is larger than TavgSlo, keeping the point with the maximum elevation and the minimum elevation of the current cluster as a characteristic point;
b. if the AvgSlo is less than TavgSlo, the point of the current cluster closest to the centroid is reserved as the feature point.
The complexity of the terrain surface features is quantitatively described, and the method is favorable for better measuring the similarity of ground points on non-space elements in the point cloud simplification process.
Example 2:
in this embodiment, two sets of data of different morphological features are set, the experimental data are preprocessed, the clustering number K of the experimental data 1 is 60, and the clustering number K of the experimental data 2 is 48, and the obtained preprocessing result is shown in fig. 2. And then calculating the variable range value of each cluster after data preprocessing by using a half-variation function analysis function of software GS + 7.0. And according to the set clustering termination threshold, performing hierarchical clustering on the two groups of data by using an SAHCA algorithm to obtain a clustering result of the SAHCA algorithm. And selecting the point with the maximum slope value of the first N points as the point cloud simplification result by taking the point number N contained in the algorithm simplification result as a threshold value. And respectively carrying out experiments on the three groups of experimental data by using a point cloud simplifying algorithm (K-Means + + algorithm) based on a K-Means + + clustering algorithm, a point cloud simplifying algorithm (Slope algorithm) based on a Slope and the algorithm, wherein the region terrain TIN model of the selected experimental data 1 is shown in figure 3, and the spatial distribution of the region sampling points is shown in figure 4. The local topographic TIN model of the selected area of experimental data 2 is shown in fig. 5, and the spatial distribution of the local sampling points is shown in fig. 6.
According to the embodiment, the simplification precision is higher than that of a K-Means + + algorithm and a Slope algorithm, and the simplification effect is the best in the aspect of simplified elevation precision.
Claims (6)
1. An airborne LiDAR ground point cloud simplification method, characterized by comprising the steps of:
s1, preprocessing the original LiDAR ground point cloud data;
s2, selecting L terrain feature factors based on the original LiDAR ground point cloud data;
s3, introducing a half-variation function, and determining the spatial autocorrelation range of each topographic feature factor based on the preprocessed original LiDAR ground point cloud data;
s4, carrying out spatial autocorrelation hierarchical clustering based on spatial autocorrelation ranges of all topographic feature factors to obtain corresponding clustering results;
s5, selecting feature points according to the clustering result to obtain a point cloud simplification result;
the step S3 specifically includes:
s31, constructing a corresponding semi-variation function for each terrain feature factor;
wherein the half-variogram y (h) is:
wherein y (h) is the variation value of the variation of the area, h is the step distance after space, Z (x) and Z (x + h) are the variable values of the area variation at the space positions x and x + h, respectively, x is the space position, and E [. cndot. ] is the expectation function;
s32, setting a half variation function value as a half of the maximum distance of the research area, namely;
in the formula, MaxDis is the maximum distance of a research area, lag is the step length, m is the grouping number under the step length, and floor is a downward integer;
s33, fitting a half-variation function curve by using a spherical model to determine the spatial autocorrelation range of each topographic characteristic factor;
the limiting conditions when determining the spatial autocorrelation range are as follows:
2. the method for airborne LiDAR ground point cloud simplification of claim 1, wherein the preprocessing step S1 is specifically performed by:
a1, calculating all points in the raw LiDAR ground point cloud data to each initial clustering center CiThe Euclidean distance of;
wherein, a subscript i is 1, 2.., K, which is a serial number of a cluster obtained by clustering;
a2, dividing each original LiDAR ground point cloud data into the nearest clusters according to the calculated Euclidean distance until the original LiDAR ground point cloud data are clustered to obtain K clusters, and finishing the preprocessing.
3. The method for airborne LiDAR ground point cloud simplification of claim 2, wherein the step S2 is specifically:
s21, organizing the original LiDAR ground point cloud data by adopting an irregular triangulation network;
s22, calculating a Spearman correlation coefficient | R | among all terrain feature factors in an irregular triangular network of the tissue;
s23, selecting L terrain feature factors according to the calculated Spearman correlation coefficient | R |.
4. The method for airborne LiDAR ground point cloud simplification of claim 2, wherein the step S4 is specifically:
and taking the minimum value of the spatial autocorrelation range corresponding to the terrain characteristic factors in the original LiDAR ground point cloud data of each cluster as a clustering termination threshold value, and performing hierarchical clustering on each cluster respectively to obtain a clustering result.
5. The method for airborne LiDAR ground point cloud simplification of claim 4, wherein the step S5 is specifically:
s51, determining the corresponding relation between each cluster in the clustering result of the SACHCA algorithm and each cluster obtained by preprocessing;
s52, taking each cluster in the clustering result of the SACHCA algorithm as an object, and calculating the average slope AvgSlo of each cluster and the average slope TavgSlo of the corresponding preprocessed cluster;
and S53, sampling the feature points according to the average gradient calculation result, and selecting the feature points in all clusters in the clustering result of the SACHCA algorithm as a point cloud simplification result.
6. The method for airborne LiDAR ground point cloud simplification of claim 5, wherein in step S53, when sampling is performed based on the average slope calculation, the sampling is performed according to the following principles:
a. if the AvgSlo is larger than TavgSlo, keeping the point with the maximum elevation and the minimum elevation of the current cluster as a characteristic point;
b. if the AvgSlo is less than TavgSlo, the point of the current cluster closest to the centroid is reserved as the feature point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110599859.9A CN113192172B (en) | 2021-05-31 | 2021-05-31 | Airborne LiDAR ground point cloud simplification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110599859.9A CN113192172B (en) | 2021-05-31 | 2021-05-31 | Airborne LiDAR ground point cloud simplification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113192172A CN113192172A (en) | 2021-07-30 |
CN113192172B true CN113192172B (en) | 2022-06-10 |
Family
ID=76985839
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110599859.9A Active CN113192172B (en) | 2021-05-31 | 2021-05-31 | Airborne LiDAR ground point cloud simplification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113192172B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574303A (en) * | 2014-12-26 | 2015-04-29 | 河海大学 | Airborne LiDAR point cloud ground filtering method based on spatial clustering |
CN107292935A (en) * | 2017-05-05 | 2017-10-24 | 深圳市建设综合勘察设计院有限公司 | Compression method, storage device and the laser radar of airborne high-density laser point cloud |
CN112164080A (en) * | 2020-09-30 | 2021-01-01 | 西南交通大学 | Vehicle-mounted LiDAR point cloud railway track vertex extraction method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9523772B2 (en) * | 2013-06-14 | 2016-12-20 | Microsoft Technology Licensing, Llc | Object removal using lidar-based classification |
CN110046563B (en) * | 2019-04-02 | 2022-06-10 | 中国能源建设集团江苏省电力设计院有限公司 | Power transmission line section elevation correction method based on unmanned aerial vehicle point cloud |
-
2021
- 2021-05-31 CN CN202110599859.9A patent/CN113192172B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574303A (en) * | 2014-12-26 | 2015-04-29 | 河海大学 | Airborne LiDAR point cloud ground filtering method based on spatial clustering |
CN107292935A (en) * | 2017-05-05 | 2017-10-24 | 深圳市建设综合勘察设计院有限公司 | Compression method, storage device and the laser radar of airborne high-density laser point cloud |
CN112164080A (en) * | 2020-09-30 | 2021-01-01 | 西南交通大学 | Vehicle-mounted LiDAR point cloud railway track vertex extraction method |
Non-Patent Citations (4)
Title |
---|
Spatial variation of soil quality indicators as a function of land use and topography;M Kiani等;《Canadian Journal of Soil Science》;20201231;第100卷(第4期);463-478 * |
一种改进的基于平面拟合的机载LiDAR点云滤波方法;陈磊等;《遥感技术与应用》;20110215;第26卷(第1期);117-122 * |
结合OTSU与迭代三角网的机载LiDAR建筑物点云提取;洪绍轩等;《遥感信息》;20181215;第33卷(第6期);79-85 * |
结合无人机载LiDAR点云法向量的K-means++聚类精简;李沛婷等;《国土资源遥感》;20200615;第32卷(第2期);103-110 * |
Also Published As
Publication number | Publication date |
---|---|
CN113192172A (en) | 2021-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109887015B (en) | Point cloud automatic registration method based on local curved surface feature histogram | |
CN106970375B (en) | Method for automatically extracting building information from airborne laser radar point cloud | |
CN109215129B (en) | Local feature description method based on three-dimensional point cloud | |
CN108320293A (en) | A kind of combination improves the quick point cloud boundary extractive technique of particle cluster algorithm | |
CN111340723B (en) | Terrain-adaptive airborne LiDAR point cloud regularization thin plate spline interpolation filtering method | |
CN111340862B (en) | Point cloud registration method and device based on multi-feature fusion and storage medium | |
CN107492120B (en) | Point cloud registration method | |
CN109323697B (en) | Method for rapidly converging particles during starting of indoor robot at any point | |
CN116310849B (en) | Tree point cloud monomerization extraction method based on three-dimensional morphological characteristics | |
CN111415379A (en) | Three-dimensional point cloud data registration method based on cuckoo optimization | |
CN113177897A (en) | Rapid lossless filtering method for disordered 3D point cloud | |
CN114663373A (en) | Point cloud registration method and device for detecting surface quality of part | |
CN110334584B (en) | Gesture recognition method based on regional full convolution network | |
CN108344975A (en) | A kind of joint cluster scaling method declined using gradient with included angle cosine | |
CN113744389B (en) | Point cloud simplifying method for complex part curved surface feature preservation | |
CN112767429B (en) | Ground-snow surface point cloud rapid segmentation method | |
CN114332172A (en) | Improved laser point cloud registration method based on covariance matrix | |
CN113192172B (en) | Airborne LiDAR ground point cloud simplification method | |
CN108510010A (en) | A kind of density peaks clustering method and system based on prescreening | |
CN117197677A (en) | Tropical rain forest arbor-shrub separation method based on laser radar point cloud data | |
CN115442887B (en) | Indoor positioning method based on RSSI of cellular network | |
CN112070787A (en) | Aviation three-dimensional point cloud plane segmentation method based on opponent reasoning theory | |
CN114627346B (en) | Point cloud data downsampling method capable of retaining important features | |
CN116561692A (en) | Dynamic update real-time measurement data detection method | |
CN112991402B (en) | Wen Wudian cloud registration method and system based on improved differential evolution algorithm |
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 | ||
GR01 | Patent grant |