CN115272177A - Non-contact type pavement section information extraction and analysis method - Google Patents
Non-contact type pavement section information extraction and analysis method Download PDFInfo
- Publication number
- CN115272177A CN115272177A CN202210681735.XA CN202210681735A CN115272177A CN 115272177 A CN115272177 A CN 115272177A CN 202210681735 A CN202210681735 A CN 202210681735A CN 115272177 A CN115272177 A CN 115272177A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- section
- cloud data
- road surface
- 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
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Multimedia (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
- Road Repair (AREA)
Abstract
The invention relates to the technical field of pavement sections, in particular to a non-contact pavement section information extraction and analysis method, which comprises the following steps: 1. generating pavement point cloud data, integrating the data, eliminating invalid point cloud points far away from the pavement, representing the space point cloud points in a Cartesian three-dimensional coordinate system, and constructing a pavement informatization basic data model; 2. establishing a coordinate set of a point cloud data section, intercepting the section, and preliminarily analyzing point cloud data information; 3. screening to obtain an abnormal area through linear fitting; refining the extracted section, expanding the range of the selected point cloud data and representing road surface information; 4. carrying out road longitudinal section analysis on the obtained dense point cloud data to obtain road surface longitudinal section characteristics; 5. and judging the geometric characteristics and types of the target disease area by taking the fitting result as a research object according to the point cloud data extracted from the longitudinal and transverse sections. The method can accurately judge the position and the type of the pavement diseases.
Description
Technical Field
The invention relates to the technical field of pavement sections, in particular to a non-contact pavement section information extraction and analysis method.
Background
A common manual identification method for road pavement detection belongs to a traditional detection method, and the method influences the smoothness and safety of road traffic and is low in pavement information acquisition efficiency. With the continuous development of road traffic industry, higher requirements are put forward on the acquisition and processing of road pavement information, and the rapid acquisition of accurate pavement information under a non-contact condition has a very wide application prospect.
At present, non-contact means such as unmanned aerial vehicle oblique photography and three-dimensional laser scanning can acquire road surface information data reflected through point cloud, and accurate identification processing and three-dimensional data fitting of road surface point cloud data can reach technical requirements, but because the data processing is loaded down with trivial details to make the degree of difficulty great and have great error, can not accurately reflect real conditions such as road surface diseases in real time.
Disclosure of Invention
The invention provides a non-contact type road surface section information extraction and analysis method which can overcome some or some defects in the prior art.
The invention discloses a non-contact type pavement section information extraction and analysis method, which comprises the following steps:
firstly, generating pavement point cloud data by scanning with an unmanned aerial vehicle, integrating the data, eliminating invalid point cloud points far away from the pavement, representing the space point cloud points in a Cartesian three-dimensional coordinate system, and constructing a pavement informatization basic data model;
step two, based on the step one, establishing a coordinate set of point cloud data sections, intercepting a plurality of sections with the distance of L, preliminarily analyzing point cloud data information on each section, and preparing for further analysis;
step three, screening to obtain an abnormal area different from a basic highway cross section line through linear fitting of point cloud data on the cross section; refining the extracted section beta, expanding the range of point cloud data selected based on the section and representing road surface information as much as possible;
step four, carrying out road longitudinal section analysis on the obtained dense point cloud data, wherein the analysis method is the same as that in the step three, and obtaining the road surface longitudinal section characteristics;
and step five, judging the geometric characteristics and types of the target disease areas by taking the fitting results as research objects according to the point cloud data extracted from the longitudinal and transverse sections.
Preferably, in the first step, in order to express the point cloud data in the form of coordinates, all the point cloud data in the database are expressed in a cartesian coordinate system, and each point cloud data is composed of three-dimensional coordinate vector elements and is marked as (a)x,ay,az)T(ii) a The point cloud data set is expressed as
Each column in the matrix represents the coordinate information of one point, and the data representing the road surface information is generalized into a model according to all three-dimensional coordinate data to reflect the characteristics of the road surface.
Preferably, in the second step, a cross section with x = b is selected from the generated coordinate basis database and is recorded as β, and all points on the cross section are extracted to a set
The aggregate reflects the road information for this section. When the section beta is intercepted, the value of b is in the whole road surface length, and the range is [0]The distance is L; the value of L determines the accuracy of road information identification.
Preferably, in the third step, the specific method is as follows:
the section of x = b is enlarged to two sides from plane beta 'to beta', the value range of the point cloud abscissa is [ b-delta, b + delta]At the moment, more point cloud data in the range represent section information; based on geometryThe mathematical interrelationship of a middle point, a straight line and a plane is shown, and the expression of the plane beta in the space (x, y, z) is x-b =0; from this point cloud aggregate matrix D, the point (a) can be obtainedx,ay,az) The distance to the plane beta satisfies | ax-b | ≦ δ; recording the extracted point cloud data as a matrix
Projecting all point cloud data to a middle section beta to obtain
Dense point cloud data of (a); and performing fitting analysis on the second and third rows of data in the F', acquiring a trace reflecting the pavement information, and reflecting the geometric characteristics of the specific pavement so as to deduce the disease characteristics and the shape of the pavement.
Preferably, in the fourth step, the extraction and analysis of the point cloud data of the cross section are combined, the data are extracted again, the maximum value or the minimum value of the vertical coordinate on the beta cross section is marked and is marked as c, a road surface longitudinal section data set is established on the basis of the y = c plane, the point cloud data in the range of [ c-delta, c + delta ] is extracted for fitting analysis, and the analysis method is the same as the third step, so that the road surface longitudinal section characteristics are obtained.
Different from the traditional pavement detection method which has low efficiency and great difficulty, the invention provides a non-contact pavement section information extraction and analysis method, which comprises a series of processes of integration of pavement point cloud data, elimination of invalid point cloud data, section processing of point cloud data, extraction of road section characteristics, disease analysis and the like; processing the pavement point cloud section data by using a statistical analysis method and a fitting method, establishing a pavement section data model, and representing pavement section characteristics in a trace manner; the method adopts non-contact to acquire the information of the section of the road surface, improves the speed and the precision of information acquisition while ensuring the traffic efficiency and the safety, provides technical support for the detection and the maintenance of the road surface, and realizes the automation of road surface monitoring.
The invention provides a method for acquiring point cloud data of a road surface by a non-contact method and extracting section characteristic information of the road surface by the point cloud data. The method has the advantages that the pavement characteristics are represented by the cross section, the reliability is high, the recognition effect is obvious, the application requirements are met, the positions and types of pavement diseases can be accurately judged, and the reliability of the achievement of the method is proved.
Drawings
Fig. 1 is a flowchart of a non-contact type road surface section information extraction and analysis method in embodiment 1;
FIG. 2 is a schematic diagram of coordinate representation of three-dimensional point cloud data in example 1;
fig. 3 is a schematic diagram of the extraction and processing of the clouding data on the section β in example 1;
FIG. 4 is a schematic diagram showing detailed analysis of the point cloud data of the section in example 1;
FIG. 5 is a schematic diagram of point cloud data model construction and processing in example 1;
FIG. 6 is a schematic diagram of processing and fitting analysis of section β point cloud data in example 1;
fig. 7 is a schematic diagram of the processing and analysis of the planar gamma point cloud data in embodiment 1.
Detailed Description
For a further understanding of the invention, reference should be made to the following detailed description taken in conjunction with the accompanying drawings and examples. It is to be understood that the examples are illustrative of the invention and not restrictive.
Example 1
As shown in fig. 1, the embodiment provides a non-contact type road surface section information extraction and analysis method, which includes the following steps:
firstly, generating pavement point cloud data by scanning through an unmanned aerial vehicle, integrating the data, eliminating invalid point cloud points far away from the pavement, representing the space point cloud points in a Cartesian three-dimensional coordinate system, and constructing a pavement informatization basic data model;
in order to express the point cloud data in the form of coordinates, all the point cloud data in the database are expressed in a Cartesian coordinate system, and each point cloud data is composed of three-dimensional coordinate vector elements and is marked as (a)x,ay,az)T(ii) a Point cloud dataIs expressed as a set
Each column in the matrix represents coordinate information of one point, and data representing road surface information is generalized into a model according to all three-dimensional coordinate data to reflect the characteristics of the road surface.
The density of the assumed points is enough to effectively reflect the road surface information. In the data model, the points are represented as in fig. 2 (taking points a and B as an example), the set of points reflects information of different positions in the road surface range, and the road surface information can be represented under the condition of enough points.
Step two, based on the step one, establishing a coordinate set of point cloud data sections, intercepting a plurality of sections with the distance of L, preliminarily analyzing point cloud data information on each section, and preparing for further analysis;
selecting a section with x = b from the generated coordinate basic database as beta, and extracting all points on the section into a set
The aggregate reflects the road information for this section. When the section beta is intercepted, the value of b is in the whole road surface length, and the range is [0]The distance is L; the value of L determines the accuracy of the road surface information recognition, as shown in fig. 3.
Step three, screening to obtain an abnormal area different from a basic highway cross section line through linear fitting of point cloud data on a cross section; refining the extracted section beta, expanding the range of point cloud data selected based on the section and representing road surface information as much as possible;
the specific method comprises the following steps:
the section of x = b is enlarged to two sides from plane beta 'to beta', the value range of the point cloud abscissa is [ b-delta, b + delta]At the moment, more point cloud data in the range represent section information; based on the interrelationship of the spatial midpoint, the straight line and the plane in the geometric mathematics, the expression of the plane beta in the space (x, y, z) is x-b =0; from this point cloud aggregate matrix D, the point (a) can be obtainedx,ay,az) To the planeThe distance of beta satisfies | ax-b | ≦ δ; recording the extracted point cloud data as a matrix
Projecting all point cloud data to a middle section beta to obtain
Dense point cloud data of (a); and performing fitting analysis on the second and third rows of data in the F' to obtain a trace reflecting the road surface information, and reflecting the geometric characteristics of the specific road surface so as to deduce the disease characteristics and the shape of the road surface, as shown in FIG. 4.
Step four, carrying out road longitudinal section analysis on the obtained dense point cloud data, wherein the analysis method is the same as that in the step three, and obtaining the road surface longitudinal section characteristics;
and (4) extracting the data again by combining extraction and analysis of point cloud data of the cross section, marking the maximum or minimum value of the vertical coordinate on the beta cross section as c, establishing a pavement longitudinal section data set on the basis of the plane y = c, extracting the point cloud data in the range of [ c-delta, c + delta ] for fitting analysis, and obtaining the pavement longitudinal section characteristics by the same analysis method as the third step.
And step five, judging the geometric characteristics and types of the target disease areas by taking the fitting results as research objects according to the point cloud data extracted from the longitudinal and transverse sections.
The following summarizes an analysis method for acquiring and processing road surface section information, and mainly provides a systematic method for recognizing and processing road surface information. Firstly, preprocessing point cloud data acquired in a non-contact mode, eliminating noise points far away from a road surface or invalid noise points, intercepting a section to perform data fitting analysis, marking a section beta with an abnormal fitting result, then expanding the range of the selected point cloud data on the basis, projecting all point cloud data in the range to the section beta, wherein the distance between the selected point cloud data and the section beta is smaller than or equal to delta.
Further analyzing the point cloud data on the section beta, and fitting the point cloud data by using MATLAB sentences to obtain a straight (or curved) line reflecting the road surface information, so that a construction and analysis method of non-contact road surface point cloud data information data is provided, and the reliability of the method is verified by the processing and analysis result of the data.
1. Data model construction of road surface point cloud information
Introducing point cloud data collected by research points, preprocessing the point cloud data, eliminating noise points of non-characteristic road surface information, numbering each point cloud data, and establishing a coordinate A (x)1,y1,z1)、B(x2,y2,z2) 8230the pavement point database of 8230may express it as a pavement digital model, as shown in fig. 5.
For point cloud data of different positions, coordinates represent information characteristics of a road surface at the position, relative elevation and the position of the point are reflected, meanwhile, for point cloud data combination of dense areas, road surface information can be accurately expressed, and the fact that a computer is efficient and accurate in data identification is guaranteed.
2. Digital representation and pretreatment of road surface geometrical characteristics
Because the road is a strip-shaped object, the cross section represents the road surface information of different mileage pile numbers, in order to improve the detection accuracy, a plurality of cross sections beta for cutting the road point cloud data are required to be established1、β2、β3823080, 8230where information is extracted with a distance of L. Meanwhile, the L is used as a threshold value, and the accuracy rate of pavement information identification can be improved by adjusting the value of the L, so that the requirement of pavement high-accuracy detection is effectively met. The specific implementation is as follows:
the point cloud data of the cross section is intercepted by the plane beta, the data intercepted are often less because the discreteness of the point cloud data is larger, and in order to reduce the workload of calculation, the step only screens the section beta which needs to be further analyzed. Therefore, the point in the plane becomes two-dimensional data, and the coordinates are points in the YOZ plane with the X-axis as a constant value, M (b, y)1,z1)、N(b,y2,z2)……。
In the two-dimensional plane β, the points are fitted to a longitudinal section information line by a linear regression method, which effectively reflects the road surface information characteristics, as shown in fig. 6, the section information is only used as a basic screening process to prepare for the next step.
3. Detailed extraction and processing of pavement section information
Through section beta1、β2、β38230823080, processing and analyzing point cloud data, and identifying abnormal area of road surface as gamma1、γ2、γ38230and 8230. Since the road surface information reflected by one plane in the three-dimensional space is limited and cannot sufficiently represent the specific information of the road surface, further analysis is required. Taking the section gamma as an example, expanding the range delta towards two sides, wherein the value range of the abscissa x of the extracted point cloud data is as follows: x is a radical of a fluorine atomγ-δ≤xγ≤xγ+δ。
Then all points of the space range are divided into
Projected onto a plane gamma to obtain the coordinate P (x) in a two-dimensional planeγ,y1,z1)、Q(xγ,y2,z2) 8230, dense two-dimensional plane point cloud data is generated, point data is fitted by means of MATLAB statements, trace characteristics of the point data are analyzed, and cross section information of the road surface is obtained. The section fitting curve analysis shows that the middle part has the depression disease, so that a monitoring method of pavement information is formed, and the position of the disease is processed and warned in real time, as shown in fig. 7.
4. Refined identification of pavement information
The extraction and processing of the point cloud data of the cross section can effectively represent pavement information and accurately identify pavement diseases, in order to reflect three-dimensional pavement information, the method combines the point cloud data of the longitudinal section, traces of two sections can be obtained through processing and analysis, and the geometric characteristics of the traces are comprehensively analyzed, so that the effective information of the pavement diseases is accurately extracted, and a pavement disease system is established to monitor the pavement in real time.
The present invention and its embodiments have been described above schematically, and the description is not intended to be limiting, and what is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. Therefore, without departing from the spirit of the present invention, a person of ordinary skill in the art should understand that the present invention shall not be limited to the embodiments and the similar structural modes without creative design.
Claims (5)
1. A non-contact type pavement section information extraction and analysis method is characterized by comprising the following steps: the method comprises the following steps:
firstly, generating pavement point cloud data by scanning with an unmanned aerial vehicle, integrating the data, eliminating invalid point cloud points far away from the pavement, representing the space point cloud points in a Cartesian three-dimensional coordinate system, and constructing a pavement informatization basic data model;
step two, based on the step one, establishing a coordinate set of point cloud data sections, intercepting a plurality of sections with the distance of L, preliminarily analyzing point cloud data information on each section, and preparing for further analysis;
step three, screening to obtain an abnormal area different from a basic highway cross section line through linear fitting of point cloud data on a cross section; refining the extracted section beta, expanding the range of point cloud data selected based on the section and representing road surface information;
step four, carrying out road longitudinal section analysis on the obtained dense point cloud data, wherein the analysis method is the same as that in the step three, and obtaining the road surface longitudinal section characteristics;
and step five, judging the geometric characteristics and types of the target disease areas by taking the fitting results as research objects according to the point cloud data extracted from the longitudinal and transverse sections.
2. The non-contact type pavement section information extraction and analysis method according to claim 1, characterized in that: in the first step, in order to express the point cloud data in a coordinate form, all the point cloud data in the database are expressed in a Cartesian coordinate system, and each point cloud data is composed of three-dimensional coordinate vector elements and is marked as (a)x,ay,az)T(ii) a The point cloud data set is expressed as
Each column in the matrix represents the coordinate information of one point, and the data representing the road surface information is generalized into a model according to all three-dimensional coordinate data to reflect the characteristics of the road surface.
3. The non-contact type pavement section information extraction and analysis method according to claim 1, characterized in that: in the second step, a section with x = b is selected from the generated coordinate basic database and is recorded as beta, and all points on the section are extracted to a set
The aggregate reflects the road information for this section. When the section beta is intercepted, the value of b is in the whole road surface length, and the range is [0]The distance is L; the value of L determines the accuracy of road surface information identification.
4. The non-contact type pavement section information extraction and analysis method according to claim 1, characterized in that: in the third step, the concrete method is as follows:
expanding the cross section of x = b to two sides from a plane beta 'to beta', wherein the value range of the abscissa of the point cloud is [ b-delta, b + delta ]]At the moment, more point cloud data in the range represent section information; based on the interrelationship of spatial midpoint, straight line and plane in the geometrical mathematics, the expression of the plane beta in the space (x, y, z) is x-b =0; the point (a) can thus be obtained in the point cloud set matrix Dx,ay,az) The distance to the plane beta satisfies | ax-b | ≦ δ; recording the extracted point cloud data as a matrix
Projecting all point cloud data to a middle section beta to obtain
Dense point cloud data of (a); simulating the second and third rows of data in FAnd (4) performing combined analysis to obtain a trace reflecting the road surface information and reflect the geometric characteristics of the specific road surface so as to deduce the disease characteristics and the shape of the road surface.
5. The non-contact type pavement section information extraction and analysis method according to claim 1, characterized in that: in the fourth step, the extraction and analysis of the point cloud data of the cross section are combined, the data are extracted again, the maximum value or the minimum value of the vertical coordinate on the beta cross section is marked and recorded as c, a road surface longitudinal section data set is established on the basis of the y = c plane, the point cloud data in the range of [ c-delta, c + delta ] is extracted for fitting analysis, and the analysis method is the same as the third step, so that the road surface longitudinal section characteristics are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210681735.XA CN115272177B (en) | 2022-06-15 | 2022-06-15 | Non-contact pavement section information extraction and analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210681735.XA CN115272177B (en) | 2022-06-15 | 2022-06-15 | Non-contact pavement section information extraction and analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115272177A true CN115272177A (en) | 2022-11-01 |
| CN115272177B CN115272177B (en) | 2023-07-14 |
Family
ID=83760784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210681735.XA Active CN115272177B (en) | 2022-06-15 | 2022-06-15 | Non-contact pavement section information extraction and analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272177B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777947A (en) * | 2016-12-08 | 2017-05-31 | 成都理工大学 | A kind of method of slip mass motion feature on calculating Broken-line sloping surface |
| CN106887020A (en) * | 2015-12-12 | 2017-06-23 | 星际空间（天津）科技发展有限公司 | A kind of road vertical and horizontal section acquisition methods based on LiDAR point cloud |
| WO2017120897A1 (en) * | 2016-01-15 | 2017-07-20 | 武汉武大卓越科技有限责任公司 | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| CN110375722A (en) * | 2019-06-25 | 2019-10-25 | 北京工业大学 | A method of duct pieces of shield tunnel joint open is extracted based on point cloud data |
| CN110490888A (en) * | 2019-07-29 | 2019-11-22 | 武汉大学 | Freeway geometry Characteristic Vectors based on airborne laser point cloud quantify extracting method |
| CN111678430A (en) * | 2020-04-20 | 2020-09-18 | 上海城建城市运营(集团)有限公司 | Road geometric linear and road surface three-dimensional structure reconstruction system and reconstruction method |
| CN112132159A (en) * | 2020-09-07 | 2020-12-25 | 山东科技大学 | Pavement pit extraction method based on continuous profile point cloud feature analysis |
| US20210303751A1 (en) * | 2020-03-27 | 2021-09-30 | Nanjing University Of Aeronautics And Astronautics | Method and device for rapid analysis of tunnel section convergence |
| CN113804154A (en) * | 2021-08-30 | 2021-12-17 | 东南大学 | Road surface subsidence detection method and device based on satellite and unmanned aerial vehicle remote sensing |
| CN113850914A (en) * | 2021-08-13 | 2021-12-28 | 江苏瑞沃建设集团有限公司 | Matrix conversion method for linear laser three-dimensional scanning point cloud data |
| CN114119998A (en) * | 2021-12-01 | 2022-03-01 | 成都理工大学 | Vehicle-mounted point cloud ground point extraction method and storage medium |
| CN114541304A (en) * | 2022-03-04 | 2022-05-27 | 成都理工大学 | Automatic robot that patrols and examines in highway road surface |
-
2022
- 2022-06-15 CN CN202210681735.XA patent/CN115272177B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106887020A (en) * | 2015-12-12 | 2017-06-23 | 星际空间（天津）科技发展有限公司 | A kind of road vertical and horizontal section acquisition methods based on LiDAR point cloud |
| WO2017120897A1 (en) * | 2016-01-15 | 2017-07-20 | 武汉武大卓越科技有限责任公司 | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| US20190197340A1 (en) * | 2016-01-15 | 2019-06-27 | Wuhan Wuda Zoyon Science And Technology Co., Ltd. | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| CN106777947A (en) * | 2016-12-08 | 2017-05-31 | 成都理工大学 | A kind of method of slip mass motion feature on calculating Broken-line sloping surface |
| CN110375722A (en) * | 2019-06-25 | 2019-10-25 | 北京工业大学 | A method of duct pieces of shield tunnel joint open is extracted based on point cloud data |
| CN110490888A (en) * | 2019-07-29 | 2019-11-22 | 武汉大学 | Freeway geometry Characteristic Vectors based on airborne laser point cloud quantify extracting method |
| US20210303751A1 (en) * | 2020-03-27 | 2021-09-30 | Nanjing University Of Aeronautics And Astronautics | Method and device for rapid analysis of tunnel section convergence |
| CN111678430A (en) * | 2020-04-20 | 2020-09-18 | 上海城建城市运营(集团)有限公司 | Road geometric linear and road surface three-dimensional structure reconstruction system and reconstruction method |
| CN112132159A (en) * | 2020-09-07 | 2020-12-25 | 山东科技大学 | Pavement pit extraction method based on continuous profile point cloud feature analysis |
| CN113850914A (en) * | 2021-08-13 | 2021-12-28 | 江苏瑞沃建设集团有限公司 | Matrix conversion method for linear laser three-dimensional scanning point cloud data |
| CN113804154A (en) * | 2021-08-30 | 2021-12-17 | 东南大学 | Road surface subsidence detection method and device based on satellite and unmanned aerial vehicle remote sensing |
| CN114119998A (en) * | 2021-12-01 | 2022-03-01 | 成都理工大学 | Vehicle-mounted point cloud ground point extraction method and storage medium |
| CN114541304A (en) * | 2022-03-04 | 2022-05-27 | 成都理工大学 | Automatic robot that patrols and examines in highway road surface |
Non-Patent Citations (2)
| Title |
|---|
| 杨望山;蔡来良;谷淑丹;: "提取城市道路边线的点云法向量聚类法", 光子学报, no. 06 * |
| 骆磊;马荣贵;薛昊;: "基于无人机的道路点云数据分割提取算法", 计算机系统应用, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115272177B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Automated extraction of structural elements in steel girder bridges from laser point clouds | |
| CN111402227B (en) | Bridge crack detection method | |
| CN107679441B (en) | Method for extracting height of urban building based on multi-temporal remote sensing image shadow | |
| CN111811420B (en) | Tunnel three-dimensional contour integral absolute deformation monitoring method and system | |
| WO2020114466A1 (en) | Tunnel point cloud data analysis method and system | |
| CN113298833A (en) | Target object point cloud characteristic line and surface extraction method and system | |
| CN113658117B (en) | Method for identifying and dividing aggregate boundary in asphalt mixture based on deep learning | |
| CN110363054B (en) | Road marking line identification method, device and system | |
| CN114612444B (en) | Fine defect analysis method based on progressive segmentation network | |
| CN111553909B (en) | Airplane skin narrow end face extraction method based on measured point cloud data | |
| CN115272177A (en) | Non-contact type pavement section information extraction and analysis method | |
| CN112116612A (en) | Pavement tree image example segmentation method based on Mask R-CNN | |
| CN117253205A (en) | Road surface point cloud rapid extraction method based on mobile measurement system | |
| CN112581521B (en) | Method for extracting central line of magnetic suspension track | |
| Yeung et al. | A preliminary investigation into automated identification of structural steel without a priori knowledge | |
| CN113743483A (en) | Road point cloud error scene analysis method based on spatial plane offset analysis model | |
| CN112967256A (en) | Tunnel ovalization detection method based on spatial distribution | |
| CN112347901A (en) | Rock mass analysis method based on three-dimensional laser scanning technology | |
| CN111813775A (en) | Tunnel point cloud data processing method and device and storage medium | |
| CN112069445A (en) | 2D SLAM algorithm evaluation and quantification method | |
| Pamart et al. | Morphological analysis of shape semantics from curvature-based signatures | |
| CN116907350B (en) | Single turnout geometry measuring method and device, electronic equipment and storage medium | |
| CN116935231B (en) | Tunnel surrounding rock structural surface information extraction and key block identification method | |
| CN116993728B (en) | Dam crack monitoring system and method based on point cloud data | |
| CN114782925B (en) | Highway guardrail vectorization method and device based on vehicle-mounted LIDAR data |
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 |