CN111563905A - Method for extracting axis of complex pipeline of engine - Google Patents
Method for extracting axis of complex pipeline of engine Download PDFInfo
- Publication number
- CN111563905A CN111563905A CN202010375967.3A CN202010375967A CN111563905A CN 111563905 A CN111563905 A CN 111563905A CN 202010375967 A CN202010375967 A CN 202010375967A CN 111563905 A CN111563905 A CN 111563905A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- point cloud
- axis
- point
- cloud data
- 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.)
- Granted
Links
Images
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
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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
Abstract
The invention relates to a method for extracting an axis of a complex pipeline of an engine, which specifically comprises the following steps: s1, partitioning pipeline point cloud data: scanning to obtain engine pipeline point cloud data, and segmenting the pipeline point cloud data and the node data by a weak-convexity approximate segmentation algorithm aiming at the scanned and obtained pipeline point cloud data; s2, calculating the axis of the segmented pipeline: respectively calculating a median point of local L1 as a pipeline axis point according to each segmented pipeline point cloud data obtained by segmentation; s3, connecting the axis of the segmented pipeline with the node: and the extraction of the axis of the complex pipeline is finished by determining the topological connection relation between the segmented pipeline and the node. The pipeline point cloud data segmentation method realizes effective segmentation of pipeline data and node data; by utilizing the divide and conquer concept, the extraction of the incomplete complex pipeline axis is realized, and the accuracy is higher.
Description
Technical Field
The invention relates to the field of three-dimensional model processing, in particular to a method for extracting an axis of a complex pipeline of an engine.
Background
The pipelines on aircraft engines act as "cardiovascular" for the aircraft, the quality of which directly affects the reliability and serviceability of the engine. With the digital development of the design experiment technology of the aero-engine, an urgent need is also provided for the inverse modeling technology in the digital design of the engine pipeline.
In recent years, a technology for acquiring point cloud data with a complete model from a three-dimensional laser scanning device to reconstruct a curved surface of the model is mature, but due to shielding of the outer wall of an aircraft engine, the scanning device can only acquire half of the point cloud data of a pipeline. Such large area data loss makes it almost impossible to perform surface reconstruction directly on the pipeline point cloud data. Aiming at similar problems, many scholars study to extract the axis of the point cloud model and then carry out curved surface reconstruction based on the information of the axis. The axis is a shape feature representation of a model, contains topological structure information of the model, and the process of extracting the axis is actually a shape feature understanding process of an original model. Therefore, the axis for extracting the original aircraft engine pipeline point cloud data has great significance for the curved surface reconstruction of the pipeline model.
Aiming at the problems of large scanning data volume, non-uniform design size, staggered pipeline lines, complex connecting nodes, scanning data loss and the like of an aircraft engine pipeline, the invention provides a method for extracting an aircraft engine pipeline axis, which can effectively extract the engine pipeline axis in three-dimensional scanning point cloud and can be used for solving the problem of curved surface reconstruction of engine pipeline point cloud data.
Disclosure of Invention
The invention aims to solve the technical problem of providing an axis extraction method of an engine complex pipeline to solve the problem of difficult curved surface reconstruction of engine pipeline point cloud data caused by large scanning data volume, non-uniform design size, staggered pipeline lines, complex connecting nodes and scanning data loss of the engine pipeline.
In order to solve the technical problems, the technical scheme of the invention is as follows: the method for extracting the axis of the complex pipeline of the engine is characterized by comprising the following steps of: the method specifically comprises the following steps:
s1, partitioning pipeline point cloud data: scanning to obtain engine pipeline point cloud data, and segmenting the pipeline point cloud data and the node data by a weak-convexity approximate segmentation algorithm aiming at the scanned and obtained pipeline point cloud data;
s2, calculating the axis of the segmented pipeline: respectively calculating a median point of local L1 as a pipeline axis point according to each segmented pipeline point cloud data obtained by segmentation;
s3, connecting the axis of the segmented pipeline with the node: and the extraction of the axis of the complex pipeline is finished by determining the topological connection relation between the segmented pipeline and the node.
Further, the pipeline data in the step S1 is point cloud data of components for transporting fuel and lubricating oil substances, the node data is point cloud data of components for connecting and supporting the pipelines, and the components for connecting and supporting the pipelines include connecting pieces, clamps and brackets.
Further, the specific method for segmenting the pipeline point cloud data in the step S1 is as follows:
s11, performing over-segmentation on the pipeline point cloud data into block data through spectral clustering on the basis of point cloud approximate weak convexity; wherein the weak convexity of the point cloud is specifically a vector x constructed by two points2x1With a two-point normal vector n1、n2Are respectively α1、α2If α2＜α1If the two points are located on the local surface, the local surface is indicated as convex;
s12, respectively calculating diameter functions of the segmented block data in corresponding shapes, and calculating a similarity matrix for expressing the similarity of point cloud data of each block according to the corresponding diameter functions;
and S13, merging over-segmentation point cloud data with high similarity according to the similarity matrix to finish segmentation of the pipeline point cloud data.
Further, the concrete method for segmenting the pipeline point cloud data through spectral clustering in the step S11 is as follows:
s111, constructing an adjacent matrix, and if the local surface where any two points are located is represented as convex and the two points are adjacent, writing 1 at the corresponding position of the adjacent matrix, otherwise, writing 0, and taking the adjacent matrix as a point convexity map;
and S112, performing spectral clustering operation on the point convexity map to obtain an over-segmentation result of the pipeline point cloud.
5. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 3, wherein: the specific steps of calculating the similarity matrix of each block data in step S12 are as follows:
s121, uniformly sampling a plurality of points aiming at the block point cloud data;
s122, traversing the sampling points aiming at the single-block point cloud data, taking the sampling points as vertexes, taking the opposite direction of the normal vector as a central axis, and taking a certain angle as a cone angle to construct a cone;
s123, calculating the weighted distances from all points falling into the cone to the top point in the block point cloud data, and taking the median value as the shape diameter function value of the block point cloud data at the sampling point;
s124, traversing all the block data, respectively constructing a feature histogram according to a plurality of shape and diameter function values, and determining the similarity between two pieces of point cloud data by a land movement distance EMD calculation method;
and S125, establishing a similar matrix according to the similarity, wherein the ijth item on the established similar matrix is the similarity between the block pipeline data of the ith block and the block pipeline data of the jth block.
Further, the specific step of calculating the median point of the local L1 as the pipeline axis point in the step S2 is as follows:
s21, calculating a local L1 median point of the point cloud data;
s22, carrying out ellipse fitting on the calculated median point, comparing the calculated point with the fitting point, and replacing the calculated median point with the fitting point if the difference is large;
and S23, performing principal component analysis on the median axis points of the block pipeline data, and sequentially connecting the axis points according to the magnitude of the principal component analysis calculated values to construct pipeline axes.
Further, the formula for calculating the value point in the local L1 of the point cloud data in the step S21 is
X＝argmin∑i∈I∑j∈J||xi-qj||θ(||xi-qj||)+R(X)；
Wherein the content of the first and second substances,
calculating the local center of the original point cloud; r (X) adjusts the distribution among the sampling points, and avoids the excessive concentration of the sampling points; j is the index set of the original point cloud, and i is the index set of the sampled point cloud.
Further, the specific step of step S3 is:
s31, constructing bridging points at the axis node connection positions obtained by calculating the data of each block;
and S32, setting a point neighborhood search range, merging the axes if meeting other bridging points in a local range, and merging the segments to obtain the axis of the pipeline, namely finishing the extraction of the pipeline axis.
Further, the merging the axes in step S32 includes: if two bridging points exist in the local range, combining the two corresponding sections of axes into one axis; if there are three or more bridging points in the local range, the three or more bridging points are moved to their average midpoint, i.e. the average of the three or more bridging points is taken.
Compared with the prior art, the invention has the following beneficial effects:
the pipeline point cloud data segmentation method realizes effective segmentation of pipeline data and node data; by utilizing the divide and conquer concept, the extraction of the incomplete complex pipeline axis is realized, and the accuracy is higher.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments are briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method for extracting an axis of a complex pipeline of an engine according to the present invention;
FIG. 2 is a scanned and acquired cloud data of an engine pipeline experiment point according to an embodiment of the present invention;
FIG. 3 is a flowchart of step S1 of FIG. 1 according to the present invention;
FIG. 4 is a flowchart of step S11 of FIG. 3 according to the present invention;
FIG. 5 is a flowchart of step S12 of FIG. 3 according to the present invention;
FIG. 6 is a block diagram of experimental data after segmentation according to an embodiment of the present invention;
FIG. 7 is a flowchart of step S2 of FIG. 1 according to the present invention;
FIG. 8 is a schematic of the median axis of L1 of a portion of the pipeline point cloud data in accordance with an embodiment of the invention;
FIG. 9 is a flowchart of step S3 of FIG. 1 according to the present invention;
Detailed Description
The present invention will be described in further detail with reference to the following drawings and specific embodiments, it being understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention.
The invention provides a method for extracting an axis of a complex pipeline of an engine, which has a specific flow shown in figure 1 and specifically comprises the following steps:
s1, partitioning pipeline point cloud data: scanning to obtain engine pipeline point cloud data, wherein the scanned and obtained pipeline point cloud data are shown in figure 2, and aiming at the scanned and obtained pipeline point cloud data, partitioning the pipeline point cloud data and the node data by a weak convexity approximate partitioning algorithm; the pipeline data is point cloud data of components used for conveying fuel oil and lubricating oil substances, the node data is point cloud data of components used for connecting and supporting the pipelines, and the components used for connecting and supporting the pipelines comprise connecting pieces, clamps and supports.
The specific method flow of pipeline point cloud data segmentation is shown in fig. 3:
s11, performing over-segmentation on the pipeline point cloud data into block data through spectral clustering on the basis of point cloud approximate weak convexity; wherein the point cloud weak convexity specifically is a vector x constructed by two points2x1With a two-point normal vector n1、n2Is inserted into the hollow cavityThe corners are respectively α1、α2If α2＜α1If the two points are located on the local surface, the local surface is indicated as convex;
the specific method flow of the pipeline point cloud data over-segmentation by spectral clustering is shown in fig. 4:
s111, constructing an adjacent matrix, and if the local surface where any two points are located is represented as convex and the two points are adjacent, writing 1 at the corresponding position of the adjacent matrix, otherwise, writing 0, and taking the adjacent matrix as a point convexity map;
and S112, performing spectral clustering operation on the point convexity map to obtain an over-segmentation result of the pipeline point cloud.
S12, respectively calculating diameter functions of the segmented block data in corresponding shapes, and calculating a similarity matrix for expressing the similarity of point cloud data of each block according to the corresponding diameter functions; the specific process of calculating the similarity matrix of each block data is shown in fig. 5:
s121, uniformly sampling a plurality of points aiming at the block point cloud data, wherein the number of the sampling points is 10;
s122, aiming at the single block point cloud data, traversing the sampling points, constructing a cone by taking the sampling points as vertexes, taking the reverse direction of the normal vector as a central axis and taking a certain angle as a cone angle, wherein the cone angle in the embodiment of the invention is
S123, calculating the weighted distances from all points falling into the cone to the top point in the block point cloud data, and taking the median value as the shape diameter function value of the block point cloud data at the sampling point;
s124, traversing all the block data, respectively constructing a feature histogram according to a plurality of shape and diameter function values, and determining the similarity between two pieces of point cloud data by a land movement distance EMD calculation method;
and S125, establishing a similar matrix according to the similarity, wherein the ijth item on the established similar matrix is the similarity between the block pipeline data of the ith block and the block pipeline data of the jth block.
And S13, merging the over-segmentation point cloud data with high similarity according to the similarity matrix to finish the segmentation of the pipeline point cloud data, wherein the pipeline segmentation effect is shown in figure 6.
S2, calculating the axis of the segmented pipeline: respectively calculating a median point of local L1 as a pipeline axis point according to each segmented pipeline point cloud data obtained by segmentation;
the specific process of calculating the median point of the local L1 as the pipeline axis point is shown in fig. 7:
s21, calculating a local L1 median point of the point cloud data; wherein, the calculation formula of the median point of L1 is:
wherein the content of the first and second substances,
calculating the local center of the original point cloud; r (X) adjusts the distribution among the sampling points, and avoids the excessive concentration of the sampling points; j is the index set of the original point cloud, and i is the index set of the sampled point cloud.
S22, carrying out ellipse fitting on the calculated median point, comparing the calculated point with the fitting point, and replacing the calculated median point with the fitting point if the difference is large;
s23, performing principal component analysis on the median axis points of the block pipeline data, sequentially connecting the axis points according to the magnitude of the calculated values of the principal component analysis, and constructing pipeline axes, wherein a schematic diagram of part of the block pipeline axes is shown in FIG. 8.
S3, connecting the axis of the segmented pipeline with the node: the extraction of the axis of the complex pipeline is completed by determining the topological connection relation between the segmented pipeline and the node, and the specific flow is shown in fig. 9:
s31, constructing bridging points at the axis node connection positions obtained by calculating the data of each block;
s32, setting a point neighborhood searching range, and if meeting other bridging points in a local range, combining the axes, wherein the combination of the axes comprises the following steps: if two bridging points exist in the local range, combining the two corresponding sections of axes into one axis; if there are three or more bridging points in the local range, the three or more bridging points are moved to their average midpoint, i.e. the average of the three or more bridging points is taken. And combining the sections to obtain the axis of the pipeline, namely finishing the extraction of the axis of the pipeline.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a mobile terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments illustrated in the drawings, the present invention is not limited to the embodiments, which are illustrative rather than restrictive, and it will be apparent to those skilled in the art that many more modifications and variations can be made without departing from the spirit of the invention and the scope of the appended claims.
Claims (9)
1. The method for extracting the axis of the complex pipeline of the engine is characterized by comprising the following steps of: the method specifically comprises the following steps:
s1, partitioning pipeline point cloud data: scanning to obtain engine pipeline point cloud data, and segmenting the pipeline point cloud data and the node data by a weak-convexity approximate segmentation algorithm aiming at the scanned and obtained pipeline point cloud data;
s2, calculating the axis of the segmented pipeline: respectively calculating a median point of local L1 as a pipeline axis point according to each segmented pipeline point cloud data obtained by segmentation;
s3, connecting the axis of the segmented pipeline with the node: and the extraction of the axis of the complex pipeline is finished by determining the topological connection relation between the segmented pipeline and the node.
2. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 1, wherein: in the step S1, the pipeline data is point cloud data of components for transporting fuel and lubricating oil substances, the node data is point cloud data of components for connecting and supporting the pipelines, and the components for connecting and supporting the pipelines include connecting pieces, clamps and brackets.
3. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 1, wherein: the specific method for segmenting the pipeline point cloud data in the step S1 is as follows:
s11, performing over-segmentation on the pipeline point cloud data into block data through spectral clustering on the basis of point cloud approximate weak convexity; wherein the weak convexity of the point cloud is specifically a vector x constructed by two points2x1With a two-point normal vector n1、n2Are respectively α1、α2If α2＜α1If the two points are located on the local surface, the local surface is indicated as convex;
s12, respectively calculating diameter functions of the segmented block data in corresponding shapes, and calculating a similarity matrix for expressing the similarity of point cloud data of each block according to the corresponding diameter functions;
and S13, merging over-segmentation point cloud data with high similarity according to the similarity matrix to finish segmentation of the pipeline point cloud data.
4. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 3, wherein: the concrete method for segmenting the pipeline point cloud data through spectral clustering in the step S11 is as follows:
s111, constructing an adjacent matrix, and if the local surface where any two points are located is represented as convex and the two points are adjacent, writing 1 at the corresponding position of the adjacent matrix, otherwise, writing 0, and taking the adjacent matrix as a point convexity map;
and S112, performing spectral clustering operation on the point convexity map to obtain an over-segmentation result of the pipeline point cloud.
5. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 3, wherein: the specific steps of calculating the similarity matrix of each block data in step S12 are as follows:
s121, uniformly sampling a plurality of points aiming at the block point cloud data;
s122, traversing the sampling points aiming at the single-block point cloud data, taking the sampling points as vertexes, taking the opposite direction of the normal vector as a central axis, and taking a certain angle as a cone angle to construct a cone;
s123, calculating the weighted distances from all points falling into the cone to the top point in the block point cloud data, and taking the median value as the shape diameter function value of the block point cloud data at the sampling point;
s124, traversing all the block data, respectively constructing a feature histogram according to a plurality of shape and diameter function values, and determining the similarity between two pieces of point cloud data by a land movement distance EMD calculation method;
and S125, establishing a similar matrix according to the similarity, wherein the ijth item on the established similar matrix is the similarity between the block pipeline data of the ith block and the block pipeline data of the jth block.
6. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 1, wherein: the specific steps of calculating the median point of the local L1 as the pipeline axis point in the step S2 are as follows:
s21, calculating a local L1 median point of the point cloud data;
s22, carrying out ellipse fitting on the calculated median point, comparing the calculated point with the fitting point, and replacing the calculated median point with the fitting point if the difference is large;
and S23, performing principal component analysis on the median axis points of the block pipeline data, and sequentially connecting the axis points according to the magnitude of the principal component analysis calculated values to construct pipeline axes.
7. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 6, wherein: the formula for calculating the median point of the local L1 of the point cloud data in the step S21 is
X＝argmin∑i∈I∑j∈J||xi-qj||θ(||xi-qj||)+R(X；
Wherein the content of the first and second substances,
calculating the local center of the original point cloud; r (X) adjusts the distribution among the sampling points, and avoids the excessive concentration of the sampling points; j is the index set of the original point cloud, and i is the index set of the sampled point cloud.
8. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 1, wherein: the specific steps of step S3 are:
s31, constructing bridging points at the axis node connection positions obtained by calculating the data of each block;
and S32, setting a point neighborhood search range, merging the axes if meeting other bridging points in a local range, and merging the segments to obtain the axis of the pipeline, namely finishing the extraction of the pipeline axis.
9. The method for extracting the axis of the complex pipeline of the engine as claimed in claim 7, wherein: the merging the axes in step S32 includes: if two bridging points exist in the local range, combining the two corresponding sections of axes into one axis; if there are three or more bridging points in the local range, the three or more bridging points are moved to their average midpoint, i.e. the average of the three or more bridging points is taken.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010375967.3A CN111563905B (en) | 2020-05-06 | 2020-05-06 | Method for extracting axis of complex pipeline of engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010375967.3A CN111563905B (en) | 2020-05-06 | 2020-05-06 | Method for extracting axis of complex pipeline of engine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111563905A true CN111563905A (en) | 2020-08-21 |
| CN111563905B CN111563905B (en) | 2022-02-01 |
Family
ID=72073227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010375967.3A Active CN111563905B (en) | 2020-05-06 | 2020-05-06 | Method for extracting axis of complex pipeline of engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111563905B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140244219A1 (en) * | 2013-02-28 | 2014-08-28 | Autodesk, Inc. | Method of creating a pipe route line from a point cloud in three-dimensional modeling software |
| CN106248001A (en) * | 2016-09-10 | 2016-12-21 | 天津大学 | Extensive process pipeline based on three-dimensional laser scanner docking flatness measurement method |
| CN109583377A (en) * | 2018-11-30 | 2019-04-05 | 北京理工大学 | A kind of control method, device and host computer that pipeline model is rebuild |
| CN109783706A (en) * | 2018-12-26 | 2019-05-21 | 北京禹数技术有限公司 | Data processing method, device and the electronic equipment of pipe network topological relation |
| CN110334818A (en) * | 2019-05-22 | 2019-10-15 | 广州中船文冲船坞有限公司 | A kind of method and system of pipeline automatic identification |
-
2020
- 2020-05-06 CN CN202010375967.3A patent/CN111563905B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140244219A1 (en) * | 2013-02-28 | 2014-08-28 | Autodesk, Inc. | Method of creating a pipe route line from a point cloud in three-dimensional modeling software |
| CN106248001A (en) * | 2016-09-10 | 2016-12-21 | 天津大学 | Extensive process pipeline based on three-dimensional laser scanner docking flatness measurement method |
| CN109583377A (en) * | 2018-11-30 | 2019-04-05 | 北京理工大学 | A kind of control method, device and host computer that pipeline model is rebuild |
| CN109783706A (en) * | 2018-12-26 | 2019-05-21 | 北京禹数技术有限公司 | Data processing method, device and the electronic equipment of pipe network topological relation |
| CN110334818A (en) * | 2019-05-22 | 2019-10-15 | 广州中船文冲船坞有限公司 | A kind of method and system of pipeline automatic identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111563905B (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2024077812A1 (en) | Single building three-dimensional reconstruction method based on point cloud semantic segmentation and structure fitting | |
| CN107688806B (en) | Affine transformation-based free scene text detection method | |
| Agathos et al. | 3D articulated object retrieval using a graph-based representation | |
| CN107123164A (en) | Keep the three-dimensional rebuilding method and system of sharp features | |
| US20090128546A1 (en) | Method And Program For Registration Of Three-Dimensional Shape | |
| Canaz Sevgen et al. | An improved RANSAC algorithm for extracting roof planes from airborne lidar data | |
| Tam et al. | Deformable model retrieval based on topological and geometric signatures | |
| CN107680168B (en) | Grid simplifying method based on plane fitting in three-dimensional reconstruction | |
| CN110111375B (en) | Image matching gross error elimination method and device under Delaunay triangulation network constraint | |
| CN112396641B (en) | Point cloud global registration method based on congruent two-baseline matching | |
| CN110032936B (en) | Method for extracting maximum circular area of non-parameter hand back vein | |
| CN109657063A (en) | A kind of processing method and storage medium of magnanimity environment-protection artificial reported event data | |
| US11941329B2 (en) | Method for analyzing fuselage profile based on measurement data of whole aircraft | |
| CN111028345A (en) | Automatic identification and butt joint method for circular pipeline in port scene | |
| Liu et al. | Coarse registration of point clouds with low overlap rate on feature regions | |
| CN111563905B (en) | Method for extracting axis of complex pipeline of engine | |
| CN116543391A (en) | Text data acquisition system and method combined with image correction | |
| Paramarthalingam et al. | Extraction of compact boundary normalisation based geometric descriptors for affine invariant shape retrieval | |
| Liu et al. | Attributed graph matching based engineering drawings retrieval | |
| Ma et al. | A fast C-GIST based image retrieval method for vision-based Indoor localization | |
| CN114296397B (en) | Part model geometric feature extraction method for neural network | |
| CN113297340B (en) | Vectorization method and device for point cloud map and method and device for converting vector map into point cloud map | |
| Su et al. | High-precision matching algorithm for multi-image segmentation of micro animation videos in mobile network environment | |
| CN117710603B (en) | Unmanned aerial vehicle image three-dimensional building modeling method under constraint of linear geometry | |
| CN117152446B (en) | Improved LCCP point cloud segmentation method based on Gaussian curvature and local convexity |
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 |