CN106126816B - Repeat the extensive ALS building point cloud modeling method under building automatic sensing - Google Patents
Repeat the extensive ALS building point cloud modeling method under building automatic sensing Download PDFInfo
- Publication number
- CN106126816B CN106126816B CN201610467713.8A CN201610467713A CN106126816B CN 106126816 B CN106126816 B CN 106126816B CN 201610467713 A CN201610467713 A CN 201610467713A CN 106126816 B CN106126816 B CN 106126816B
- Authority
- CN
- China
- Prior art keywords
- building
- buildings
- model
- point cloud
- roof
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 230000003252 repetitive effect Effects 0.000 claims abstract 7
- 230000008447 perception Effects 0.000 claims abstract 5
- 238000001514 detection method Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 238000013210 evaluation model Methods 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 11
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 241000755266 Kathetostoma giganteum Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Architecture (AREA)
- Mathematical Analysis (AREA)
- Structural Engineering (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Civil Engineering (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明是一种重复建筑自动感知下的大规模ALS建筑点云建模方法，包括以下步骤：（一）采用深度学习方法，精细分割ALS点云，获取“建筑”、“植被”、“地面”和“其他”四类目标；（二）针对建筑点云，在局部区域内探测重复建筑，并对探测出的重复建筑配准和对齐，接着采用数据驱动方法，构建重复建筑屋顶模型，针对剩余的非重复建筑，采取综合数据驱动和模型驱动的混合建模方法，构建建筑屋顶的几何模型；（三）定性和定量评价建筑屋顶几何模型建模方法的精度和效率。优点：1）建模的效率和精度高，适合对重复建筑较多的城市居民区进行建模。2）方便与其他方法整合，以提升建模方法的应用范围和模型的层次细节。
The present invention is a large-scale ALS building point cloud modeling method under the automatic perception of repetitive buildings, which includes the following steps: (1) Using a deep learning method, finely segment the ALS point cloud, and obtain "building", "vegetation", "ground" ” and “other” four types of targets; (2) For the building point cloud, duplicate buildings are detected in a local area, and the detected duplicate buildings are registered and aligned, and then a data-driven method is used to construct the roof model of the duplicate buildings. For the remaining non-repetitive buildings, a hybrid modeling method of comprehensive data-driven and model-driven is adopted to construct the geometric model of the building roof; (3) Qualitatively and quantitatively evaluate the accuracy and efficiency of the modeling method of the building roof geometric model. Advantages: 1) The modeling efficiency and accuracy are high, and it is suitable for modeling urban residential areas with many repeated buildings. 2) It is convenient to integrate with other methods to improve the application scope of the modeling method and the level of detail of the model.
Description
Technical field
The present invention relates to a kind of extensive ALS building point cloud modeling methods repeated under building automatic sensing, belong to remote sensing
Science and technology field.
Background technique
With the development of Spatial Information Technology and gradually going deep into for application, demand of the people to data is higher and higher, tradition
2-D data be difficult to fully meet the demand of daily life and production, with 3S technology, high-performance calculation and three-dimensional visible
The development of change technology, expeditiously the two dimension or three-dimensional data of acquisition and processing magnanimity have gone completely into possibility, such as Google
The Bing Maps service that the Google Earth of exploitation and Microsoft release, can be such that people roam in and be made of threedimensional model
Virtual world, experience artistic conception on the spot in person, three-dimensional data spatial information abundant facilitates more real surface up to objective
The world, enabling people to browsing, decision and analysis, city under three-dimensional environment is earth surface population, economy, technology, basis
The factors such as facility and information are distributed most close quarters, rapidly and accurately obtain and the city three-dimensional data for handling magnanimity is Digital City
City builds bottleneck problem urgently to be resolved.Building is the composition most important core cell in city, and establishes the three-dimensional geography in city
The basis of information system, therefore rapidly and accurately obtain city three-dimensional building data and establish three-dimensional building model (Digital
Building Model, DBM) urban planning, city management, intelligent transportation, automatic rescue, real estate displaying, tourism are pushed away
Many necks such as Jie, digital city, disaster simulation analysis and location based service (Location Based Service, LBS)
Domain practical significance with higher and application value.
However for a long time, it is restricted by factors such as the software and hardware technology levels of data acquiring mode and processing data, it is three-dimensional
Urban architecture model is difficult to quickly establish and update, the serious further development for hindering digitalized city, from acquisition modes,
Manual field operation measurement is one of the main means for being originally taken three-dimensional building model, automatic although the data precision obtained is high
Change degree is low, time-consuming and laborious；Hereafter, digital photogrammetry, especially Aviation Digital are photogrammetric, instead of a large amount of artificial survey
Draw, become obtain three-dimensional space data one of major way, for three-dimensional building model acquisition provide it is more economical efficiently
Mode, but due to the defects of aviation image of acquisition has fuzzy, distortion, depth is broken or mutually blocks, it is frequent to interpret image
There is ambiguity and imperfection, cause automatic Building modulo n arithmetic bad adaptability, is fully automatically extracted from individual or multiple images
The building threedimensional model of the task is still very heavy, the renewal speed of Buildings Modeling precision and model is seriously constrained, although mesh
Before can be by proceduring modeling method, such as L-System, Fractals and GML(Generative Modeling Language)
Etc. technologies Fast simulation large-area three-dimensional build scene, but using the technology building urban architecture model have can not measure
Property, it is impossible to be used in the analysis of true three-dimension building data.
Airborne laser radar ALS technology is a kind of active remote sensing technology risen in later period the 1990s, as distant
Feel the Disciplinary Frontiers of development, it can quickly and accurately obtain the information such as three-dimensional coordinate and the echo strength of atural object surface point, cut
To currently, LiDAR technology experienced the development course of discrete point cloud, Full wave shape and quantum counting laser radar, echo times
By single echo to second trip echo, or even multiecho is arrived, point Yun Midu (resolution ratio) is greatly improved, or even can
Reach 50pts/m2, to provide new data source quickly to rebuild high accuracy three-dimensional buildings model.
Currently, carrying out Buildings Modeling in conjunction with ALS data, main stream approach can be attributed to following four classes: utilize digital surface mould
Type simplifies modeling, the modeling of reversed semantic procedure, the modeling method based on data-driven modeling and based on model-driven.
Simplified based on digital surface model (Digital Surface Model, DSM) and modeled, is to by original LiDAR
Data, which generate, builds the abstract of DSM and simplifies, under the premise of guaranteeing that building simplifies precision, using elimination vertex (Vertex
Decimation), the methods of Vertex Clustering (Vertex Clustering) or boundary contraction (Edge Collapse) are reduced superfluous
Remaining vertex or dough sheet then cooperate geometry and semantic constraint, realize the DSM model simplification of building.
Reversed semantic procedure modeling method can be described as: the three-dimensional data that given user obtains is advised according to the grammer of use
Then and parameter, so that the given three-dimensional data of the model and user that are generated by the rule is with uniformity.
Based on the method for data-driven modeling, also known as bottom-up processing, and the shape of building is not assumed that and straight
It connects and data is handled, by analyzing the feature of building point cloud data, uniquely determine building shape, generally require logical
It crosses and obtains the dough sheet on each roof of building, sets up topological relation, then intersected by dough sheet and obtain ridge line, will finally built
It builds object to be rebuild, such modeling method bases oneself upon data, using the methods of pattern-recognition, machine learning and statistical analysis, from number
According to the middle geometrical characteristic element (point, line and face etc.) for extracting building, then above-mentioned element is carried out according to certain topological structure
Tissue, completes the drafting of buildings model.
Modeling method based on model-driven is a kind of top-down modeling method, by defining some basic roofs
Structural parameters model primitive library (flat-head type, chevron shaped, four sides shelving, cylinder, circular cone and ball etc.), then will building point cloud with
Parameter model primitive storehouse matching, finally determines model optimized parameter by certain optimisation strategies, to complete to model, builds to improve
The precision of mould can be by building " solid geometry model " (Constructive Solid for more complicated building roof
Geometry, CSG) idea about modeling, by complex building regard as by simply build primitive by canonical Boolean calculation (simultaneously, hand over
And difference) assemble, it is based on the idea about modeling, it is necessary first to primitive segmentation be carried out to building roof, then adopted to each primitive
The modeling method driven with conventional model, finally combines basic-element model, constitutes complete building roof model.
For the above-mentioned four class mainstream modeling schemes referred to, major defect is summarized as follows:
(1) it is built although simplifying the free form that modeling method comparison is suitble to processing complicated using digital surface model, it is raw
At different scale multi-level details LOD(Level of Detail, LOD) model, convenient for network transmission and visualization rendering,
But integrality and noise to ALS data etc. are more sensitive, it is difficult to guarantee the systematicness of model geometric appearance, in addition specifically by model
It is simplified to which kind of degree, also ununified standard, in addition such method time complexity is high, is not suitable for building city large area
It builds and is modeled；
(2) reversed semantic procedure modeling convenient for the structure (floor number, window number etc. in every layer) to buildings model into
Edlin, but the no More General Form of establishment of semantic rules need to define corresponding semantic rules for different building structure, and
And optimization link time complexity with higher, be not suitable for rebuilding the building of large area；
(3) data-driven modeling method does not need the roof structure type for assuming building in advance, theoretically can be to any room
Top type is modeled, but the segmentation of roof structure element often time complexity with higher, or even is needed by man-machine
Interaction is to complete, in addition, such method is also more sensitive to the noise of ALS data, density, uniformity and integrality etc., data
Quality seriously affects the precision of final mask；
(4) model-driven modeling method is insensitive to the ALS quality of data, and constructed model has tight type, light-type
The features such as (being made of less tri patch) and seamlessness, is still only applicable to Parameter Expression and simply builds, even if by
" CSG " idea about modeling handles labyrinth building, and limited parameter model library primitive library is also difficult to exactly match to be become in real world
Change the building of multiterminal.
Summary of the invention
Proposed by the present invention is a kind of extensive ALS building point cloud modeling method repeated under building automatic sensing, it is intended to
Using ALS point cloud data in the Buildings Modeling field problem, the present invention uses ALS data source, studies in digital city
In process of construction, the modeling method on large area complex building roof in the case that different source data lacks, according to daily it has been observed that
In city, especially residential block, the identical building that repeats tends to take up sizable ratio, therefore the present invention detects repetition first
Building, counterweight, which is rebuilded to build, carries out registration alignment, builds point cloud with enhancing, is then modeled using data-driven, for non-heavy
It rebuilds and builds, integrated data of the present invention and model-driven modeling method model it, and therefore, the present invention is based on repeat building sense
The thought known rebuilds large area ALS building vertex cloud, while improving modeling accuracy, improves the modeling of ALS point cloud
Efficiency improves ALS data Buildings Modeling method, meets in practical engineering application to large area complex three-dimensional buildings model quickly more
New urgent need.
Technical solution of the invention: repeating the extensive ALS building point cloud modeling method under building automatic sensing,
Method the following steps are included:
(1) deep learning method is used, fine segmentation ALS point cloud obtains " building ", " vegetation ", " ground " and " other "
Four class targets；
(2) for building point a cloud, in regional area detection repeat build, and to detect repetition building registration and
Alignment, then uses data-driven method, and building repeats building roof model and takes synthesis for remaining non-duplicate building
The hybrid modeling method of data-driven and model-driven constructs the geometrical model of building roof；
(3) qualitative and quantitative assessment building roof geometrical model modeling method precision and efficiency.
Advantages of the present invention:
(1) modeling method that the present invention uses uses " repeating to build " and " non-duplicate building " using decision tree thought
Different modeling methods reduces algorithm to the sensibility of data, promotes the efficiency and precision of modeling, inventive algorithm is particularly suitable for
Repetition is built more city and is modeled, especially the residential block in city；
(2) modeling framework proposed by the invention has scalability, can be combined with existing other methods, to fill
It is real and improve method of the invention, for example, the detection and urban architecture of building can will be repeated when carrying out repeating to build detection
" Gestalt " layout combines, and can be improved the precision and efficiency of repetition building detection, in addition, all using after repeating Buildings Modeling
Unified model carries out geometric expression, so very convenient fusion TLS(Terrestrial Laser Scanning, TLS) or
MLS(Mobile Laser Scanning, MLS) scanning technique obtain elevation of building point cloud, with realize to ALS building roof
Existing 2.5D building roof model conversation is to build in conjunction with the 3D on roof and facade point cloud by the amendment of model, editor and perfect
Model is built, and this editor can synchronize " feedback " and repeat in building to all.
Detailed description of the invention
Attached drawing 1 is the general technical flow chart for repeating the extensive ALS building point cloud modeling method under building automatic sensing.
Attached drawing 2 is deep learning network model schematic diagram.
Attached drawing 3 is combination drive modeling technique flow chart.
Specific embodiment
Attached drawing is compareed, repeats to build the extensive ALS building point cloud modeling method under automatic sensing, method includes following
Step:
(1) deep learning method is used, fine segmentation ALS point cloud obtains " building ", " vegetation ", " ground " and " other "
Four class targets；
(2) for building point cloud, detection repeats to build in regional area, and the building surveyed in area is divided into repetition building
With non-duplicate groups of building, and the repetition building unit that detects is registrated and alignment；
(3) counterweight, which is rebuilded, builds unit set, and using data-driven method, building repeats building roof model, for residue
Non-duplicate building, take integrated data driving and model-driven hybrid modeling method, construct the geometrical model of building roof；
(4) qualitative and quantitative assessment building roof geometrical model modeling method precision and efficiency.
The use deep learning method: assuming that including in deep learning systemNLayer structureS 1 、S 2 、S 3 、…、S n ,I
WithORespectively system is output and input, then whole system can be usedI->S 1 ->S 2 -> S 3 ->…->S n ->OIt indicates, i.e. system
Input can accurately be described with output, this shows to inputIBy each layerS i Do not lose information, i.e., it is one layer anyS i All
It is another expression of original input information, it willIAs input layer,SIt is intermediate hidden layer,OAs output layer,SIn, appoint
It anticipates two adjacent hidden layersS i WithS i+1 A limited Boltzmann machine is constituted, guarantees that any one layer of input can be with defeated
Accurate description out, all limited Boltzmann machines that hidden layer is obtained are together in series, to construct Boltzmann machine network
Model；Using Boltzmann machine network model, realizes the abstract and comprehensive of ALS point cloud feature, which is input to Random
Forest supervised classifier, realize to a classification for cloud feature, finally by ALS point cloud be finally divided into " ground ", " building ",
" vegetation " and " other ".
The Random Forest supervised classifier is based on decision tree classification thought, is carried out by many a Weak Classifiers
The assembled classifier that ballot obtains, classifier robustness with higher and stronger model generalization ability, available spy
It the importance ranking of sign and is very suitable to handle the ground object sample of unbalanced classification.
Detection repeats to build in the regional area: the factors such as building size and density in statistical analysis cell are drawn
The corresponding detectivity curve for repeating architectural scale in conjunction with the above-mentioned factor obtains optimal detection according to the potential inflection point of curve
Scale, detection process need to combine line layout figures such as " road and residential area administration cells ", and constraint repeats building probe algorithm, mentions
It rises and repeats building detection efficient, the same or similar groups of building are often completed by a developer after all, these buildings often have
There are identical design drawing and scheme, repeats the inside that groups of building are normally at unit cell, the possibility of across unit cell distribution
Property is smaller.
The line layout figure is to pass through manual vectorization method or vector quantization aviation or space remote sensing image (Google
Earth, SPOT, Quick Bird, Landsat, IKONOS, Bing Maps) method obtains, or directly uses existing road
Road, land deeds isovector figure are as line layout figure.
The geometrical model of the building building roof: it is adopted using decision tree combined method for different classes of building
With matching modeling method, building set is repeated in each group of subrange obtained for detection, first to more in set
Building repeats building point cloud and is registrated and is aligned, and the repetition building after alignment is due to roof point cloud density height, and integrality is good, directly
Single building is built using the method for data-driven and directly carries out roof dough sheet partitioning boundary line and key point extraction, constructs building
The geometrical model on top, for other non-duplicate buildings, then the combination drive that can be combined using data-driven and model-driven
Modeling method successively models the non-duplicate building in each building, draws the geometrical model of building roof；The advantages of doing so
Are as follows: 1. avoid certain situations for repeating building and modeling failure as caused by the missing of data when individually being modeled；2. mentioning
Rise the density of point cloud, the quality of enhancing point cloud.
The registration and alignment, algorithm flow pseudocode are as follows:
Input: the repetition building in current subrangeB={B i }；
Output: the repetition building after registrationR；
1. Begin；
2. times taking setBIn one buildingB base As benchmark；
3. B=B\B base // from setBIt is middle to incite somebody to actionB base It excludes, at this timeB={B j }；
4. For B j in Bdo；
5. times taking setBIn one buildingB j , at this timeB j WithB base A pair of of repetition building pair is constituted, building is repeated according to it
The information such as center of gravity and characteristic point calculate translation matrix, realizeB j WithB base Rough to be registrated, the building after gross alignment is respectivelyB j ’
WithB base ’；
6. use ICP(Iterative Closest Points, ICP) algorithm pairB j ’WithB base ’It is finely adjusted, makes two
Building repeats Accurate align between building, builds point set after being alignedR’；
7. B base =R’；
8. End；
9. R=B base =R’；
10.End。
The evaluation method of the building roof geometrical model: the evaluation of building roof geometrical model mainly includes building point cloud
Evaluation two parts of segmentation and building roof geometrical model itself；The evaluation method of specific building roof point cloud segmentation result:
Kappa coefficient, ROC curve, integrality (Completeness=TP/(TP+FN)), correctness (Correctness=
TP/(TP+FP)) and overall classification accuracy (Quality=TP/(TP+FN+FP)) etc. indexs global scope assessment build point
The segmentation precision of cloud, and then the modeling accuracy of Indirect evaluation building roof model.
The precision of the global scope assessment model: 1. using residual error quantitative evalution model sampled point and building point cloud it
Between consistency；2. digital elevation model (the Digital Elevation that roof model and corresponding building point cloud generate
Model, DEM) between alignment, the consistency of qualitative evaluation point cloud and model；3. comparing mould for certain landmarks
The true value coordinate of type angle point and traditional total station survey, the precision of quantitative analysis modeling；4. the consistency of roof topological relation and
The quantity of geometry roof building model tri patch is constructed, whether evaluation model has the features such as " close " and " light weight ".In addition,
The present invention evaluates " time complexity " of the method for the present invention, together in terms of algorithm modeling efficiency to illustrate that inventive algorithm exists
The advantage of large area ALS point cloud building roof modeling.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610467713.8A CN106126816B (en) | 2016-06-24 | 2016-06-24 | Repeat the extensive ALS building point cloud modeling method under building automatic sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610467713.8A CN106126816B (en) | 2016-06-24 | 2016-06-24 | Repeat the extensive ALS building point cloud modeling method under building automatic sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106126816A CN106126816A (en) | 2016-11-16 |
| CN106126816B true CN106126816B (en) | 2019-04-05 |
Family
ID=57268737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610467713.8A Expired - Fee Related CN106126816B (en) | 2016-06-24 | 2016-06-24 | Repeat the extensive ALS building point cloud modeling method under building automatic sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106126816B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025685B (en) * | 2017-04-11 | 2020-03-17 | 南京林业大学 | Airborne building roof point cloud modeling method under topology perception |
| CN106772433B (en) * | 2017-04-11 | 2019-01-18 | 南京林业大学 | Building line based on airborne laser radar data draws drawing generating method |
| CN107170003A (en) * | 2017-05-08 | 2017-09-15 | 广东工业大学 | The model matching method and system of a kind of sail shape outside plate |
| CN108038908B (en) * | 2017-11-21 | 2021-11-30 | 泰瑞数创科技(北京)有限公司 | Space object identification and modeling method and system based on artificial intelligence |
| JP7376496B2 (en) | 2018-03-20 | 2023-11-08 | ピーシーエムエス ホールディングス インコーポレイテッド | System and method for optimizing dynamic point clouds based on prioritized transformations |
| CN112106063B (en) * | 2018-03-20 | 2025-05-16 | Pcms控股公司 | System and method for dynamically adjusting the level of detail of a point cloud |
| CN109242855B (en) * | 2018-07-19 | 2020-08-11 | 中国科学院自动化研究所 | Roof segmentation method, system and equipment based on multi-resolution 3D statistical information |
| CN109545021A (en) * | 2018-11-02 | 2019-03-29 | 国家消防工程技术研究中心 | Evacuation system detection device |
| CN109753687A (en) * | 2018-12-04 | 2019-05-14 | 中国航空工业集团公司西安飞机设计研究所 | A composite aeroelastic dynamic modeling method |
| CN112347540B (en) * | 2020-11-09 | 2023-09-08 | 重庆智慧之源科技有限公司 | Intelligent detection modeling system for building |
| CN114004938B (en) * | 2021-12-27 | 2022-04-01 | 中国电子科技集团公司第二十八研究所 | Urban scene reconstruction method and device based on mass data |
| CN115097415B (en) * | 2022-07-06 | 2025-06-03 | 山东矩阵软件工程股份有限公司 | A method, system and related device for processing waveform point cloud data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103969656A (en) * | 2014-05-08 | 2014-08-06 | 北京数字绿土科技有限公司 | Building modeling method and device based on airborne laser radar |
| CN104036544A (en) * | 2014-06-25 | 2014-09-10 | 西安煤航信息产业有限公司 | Building roof reconstruction method based on airborne LiDAR data |
| CN104197897A (en) * | 2014-04-25 | 2014-12-10 | 厦门大学 | Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4188673B2 (en) * | 2002-12-02 | 2008-11-26 | ヒタチグローバルストレージテクノロジーズネザーランドビーブイ | RECORDING / REPRODUCING DEVICE, CONTENT REPRODUCING DEVICE, DISC DEVICE, ITS CONTROL METHOD, AND PROGRAM |
-
2016
- 2016-06-24 CN CN201610467713.8A patent/CN106126816B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104197897A (en) * | 2014-04-25 | 2014-12-10 | 厦门大学 | Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud |
| CN103969656A (en) * | 2014-05-08 | 2014-08-06 | 北京数字绿土科技有限公司 | Building modeling method and device based on airborne laser radar |
| CN104036544A (en) * | 2014-06-25 | 2014-09-10 | 西安煤航信息产业有限公司 | Building roof reconstruction method based on airborne LiDAR data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106126816A (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106126816B (en) | Repeat the extensive ALS building point cloud modeling method under building automatic sensing | |
| CN106127857B (en) | The on-board LiDAR data modeling method of integrated data driving and model-driven | |
| CN109410327B (en) | BIM and GIS-based three-dimensional city modeling method | |
| CN108759840B (en) | An indoor and outdoor integrated three-dimensional navigation path planning method | |
| CN107025685B (en) | Airborne building roof point cloud modeling method under topology perception | |
| CN109900276B (en) | Station real-time emergency path planning method based on point-line-surface obstacle model construction | |
| CN110874391A (en) | Data fusion and display method based on urban space three-dimensional grid model | |
| CN112598796A (en) | Method for building and automatically updating three-dimensional building information model based on generalized point cloud | |
| CN109979006A (en) | Indoor road net model construction method and device | |
| CN115482355A (en) | Many-source data driven LOD 2-level city building model enhanced modeling algorithm | |
| Khayyal et al. | Creation and spatial analysis of 3D city modeling based on GIS data | |
| Toschi et al. | Geospatial data processing for 3D city model generation, management and visualization | |
| Adamopoulos et al. | Multi-sensor documentation of metric and qualitative information of historic stone structures | |
| Boguslawski et al. | BIM-GIS modelling in support of emergency response applications | |
| CN116994156B (en) | Landslide hidden danger comprehensive remote sensing identification method, system, equipment and medium | |
| CN108182724A (en) | A kind of high-precision urban heat island detection method, equipment and storage device | |
| CN113988084A (en) | BIM and GIS ontology fusion method and system based on SWRL rules | |
| Ying et al. | Urban 3d modelling methods: A state-of-the-art review | |
| Sabri et al. | A multi-dimensional analytics platform to support planning and design for liveable and sustainable urban environment | |
| CN104729529B (en) | The method and system that map surveying systematic error judges | |
| Erener et al. | An approach to urban building height and floor estimation by using LiDAR data | |
| Taubenböck et al. | Remote sensing—An effective data source for urban monitoring | |
| Adreani et al. | Rendering 3D city for smart city digital twin | |
| CN112686988B (en) | Three-dimensional modeling method, three-dimensional modeling device, electronic equipment and storage medium | |
| Agugiaro et al. | A web-based interactive tool for multi-resolution 3D models of a Maya archaeological site |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20161116 Assignee: Nanjing Tianfang Earth Circle Surveying and Mapping Technology Co.,Ltd. Assignor: Nanjing Forestry University Contract record no.: 2019320000272 Denomination of invention: Cloud modeling method of large-scale ALS building points of repetitive buildings based on automatic sensitivity Granted publication date: 20190405 License type: Common License Record date: 20190726 Application publication date: 20161116 Assignee: Nanjing Yihaopu Software Technology Co.,Ltd. Assignor: Nanjing Forestry University Contract record no.: 2019320000271 Denomination of invention: Cloud modeling method of large-scale ALS building points of repetitive buildings based on automatic sensitivity Granted publication date: 20190405 License type: Common License Record date: 20190726 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20161116 Assignee: Nanjing Wenjing Information Technology Co.,Ltd. Assignor: Nanjing Forestry University Contract record no.: X2019320000017 Denomination of invention: Cloud modeling method of large-scale ALS building points of repetitive buildings based on automatic sensitivity Granted publication date: 20190405 License type: Common License Record date: 20190809 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190405 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |