CN112419384B - Digital earth surface model house DLG automatic extraction method based on artificial intelligence - Google Patents
Digital earth surface model house DLG automatic extraction method based on artificial intelligence Download PDFInfo
- Publication number
- CN112419384B CN112419384B CN202011400508.2A CN202011400508A CN112419384B CN 112419384 B CN112419384 B CN 112419384B CN 202011400508 A CN202011400508 A CN 202011400508A CN 112419384 B CN112419384 B CN 112419384B
- Authority
- CN
- China
- Prior art keywords
- house
- points
- pseudo
- corner
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- 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)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides an artificial intelligence-based automatic DLG extraction method for a digital earth surface model house. Firstly, collecting point information of a house model, generating a house face point cloud, and then dividing the house face point cloud into three types according to the position relation between the point cloud and a house: the points are outside the house, on the wall surface of the house and on the corner line; for the condition that the point is outside the house, directly eliminating the point; for the case that the points are on the wall surface of a house, the set of the points is used as a correction matrix of the pseudo house roof in the later stage and is used for wall surface correction; for the case that the points are on corner lines, automatically performing linear fitting on the points on each corner line, and then searching for vertexes, namely intersecting points of more than three corner lines, according to the fitted corner lines; and (3) connecting more than three points to generate a pseudo house roof, removing and correcting the pseudo house roof, and finally generating a house DLG by using a plurality of house roofs by using a common corner line. By using the method, subjective errors are small, environmental influence is small, and high-efficiency automatic house extraction can be realized.
Description
Technical Field
The invention belongs to the technical field of computer vision recognition, and relates to an artificial intelligence-based digital earth surface model house DLG automatic extraction method and a cross-boundary application.
Background
With the continuous development and combination of computer technology and spatial information technology, users are no longer pursuing only two-dimensional paper materials, but increasingly pursuing data visualization and data storability. Early methods of field collection of large scale topographic map by mapping technology are not only greatly affected by environment, but also have lower efficiency.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention aims to provide an artificial intelligence-based automatic digital earth surface model house DLG extraction method, which combines unmanned aerial vehicle oblique photogrammetry technology and computer technology.
To achieve the above object, the solution of the present invention is:
an artificial intelligence-based digital surface model house DLG automatic extraction method comprises the following steps: firstly, collecting point information of a house model, generating a house face point cloud, and then dividing the house face point cloud into three types according to the position relation between the point cloud and a house: the points are outside the house, on the wall surface of the house and on the corner line; for the condition that the point is outside the house, directly eliminating the point; for the case that the points are on the wall surface of a house, the set of the points is used as a correction matrix of the pseudo house roof in the later stage and is used for wall surface correction; for the case that the points are on corner lines, automatically performing linear fitting on the points on each corner line, and then searching for vertexes, namely intersecting points of more than three corner lines, according to the fitted corner lines; and (3) connecting more than three points to generate a pseudo house roof, removing and correcting the pseudo house roof, and finally generating a house DLG by using a plurality of house roofs by using a common corner line.
The method is used for eliminating the situation that the false house surface has repetition and errors: the house surface with four corner points generates four triangular surfaces and a quadrilateral surface, at the moment, the four triangular surfaces are all contained on the quadrilateral surface, and only one quadrilateral surface is reserved as a house roof; in another case, the pseudo-room roof generated by points on non-adjacent corner lines is a section of a house, and whether to reject the pseudo-room roof is judged by utilizing the logical relationship between the point set on the wall surface and the pseudo-room surface.
After the process of verifying each pseudo house surface, the method generates a pseudo house surface closest to the actual house surface by using the point set on the house surface as a correction matrix if the pseudo house surface is an irregular polygon.
The invention has the beneficial effects that:
by using the method, the house extraction of the digital surface model can be rapidly realized; meanwhile, errors caused by subjectivity of users are reduced, the influence of the environment is small, and high-efficiency automatic house extraction can be realized.
Drawings
Fig. 1 is a flowchart of an automatic extraction method of a digital surface model house DLG based on artificial intelligence provided by an embodiment.
Detailed Description
In order to make the objects, technical schemes and advantages of the invention more clear, the automatic DLG extraction method for the digital surface model house based on artificial intelligence is further described in detail by the following embodiments and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, the invention provides an artificial intelligence-based automatic digital surface model house DLG extraction method.
As one possible implementation, examples are directed to digital earth model house automatic extraction techniques. Digital Surface Model (DSM) is a simulation of a surface feature (mainly a house surface); the computer vision technology can realize the identification of stereoscopic features. The two are combined, so that the quick and automatic extraction of the DSM house can be realized. Firstly, collecting point information of a house model, generating a house face point cloud, and then dividing the house face point cloud into three types according to the position relation between the point cloud and a house: the points are outside the house, on the wall surface (within the tolerance allowable range) and on the corner line;
for the condition that the point is outside the house, directly eliminating the point;
for the condition that the points are on the house surface, the set of the points is used as a correction matrix of the pseudo house surface in the later period so as to achieve the purpose that the pseudo house surface is closer to the real house surface;
for the case of points on corner lines, the method automatically performs a linear fit to the points on each corner line, and then searches for vertices, i.e., intersections of three or more corner lines, based on the fitted corner lines. The pseudo house surface is generated by connecting three or more points, and at this time, the pseudo house surface may be duplicated or erroneous. The repeated condition is that a house roof with four corner points can generate four triangular surfaces and a quadrilateral surface, and at the moment, the four triangular surfaces are all contained on the quadrilateral surface, so that only one quadrilateral surface is reserved as the house roof; another error condition is that the pseudo-room roof generated by points on non-adjacent corner lines is a section of a house, and at this time, whether to reject the pseudo-room roof can be judged by utilizing the logical relationship between the point set on the wall surface and the pseudo-room surface. After verifying each pseudo house face, the pseudo house face or the irregular polygon is required to use the point set on the house roof as a correction matrix to generate a pseudo house roof closest to the actual house roof. And finally, generating the house DLG by using the common corner line of the plurality of house roofs.
Claims (1)
1. The automatic digital surface model house DLG extraction method based on artificial intelligence is characterized in that point information is firstly collected for a house model to generate house surface point cloud, and then the three types of the house surface point cloud are classified according to the position relation between the point cloud and a house: the points are outside the house, on the wall surface of the house and on the corner line;
for the condition that the point is outside the house, directly eliminating the point;
for the case that the points are on the wall surface of a house, the set of the points is used as a correction matrix of the pseudo house roof in the later stage and is used for wall surface correction;
for the case that the points are on corner lines, automatically performing linear fitting on the points on each corner line, and then searching for vertexes, namely intersecting points of more than three corner lines, according to the fitted corner lines; generating a pseudo house roof by connecting more than three points, removing and correcting the pseudo house roof, and finally generating a house DLG by using a plurality of house roofs by using a common corner line;
eliminating the situation that the false house surface has repetition and errors: the house surface with four corner points generates four triangular surfaces and a quadrilateral surface, at the moment, the four triangular surfaces are all contained on the quadrilateral surface, and only one quadrilateral surface is reserved as a house roof; the other condition is that the pseudo-house roof generated by points on non-adjacent corner lines is a section of a house, and whether the pseudo-house roof is rejected is judged by utilizing the logical relation between the point set on the wall surface and the pseudo-house surface;
after verifying each pseudo house face, if the pseudo house face is an irregular polygon, the point set on the house face is used as a correction matrix to generate a pseudo house face similar to the actual house face.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011400508.2A CN112419384B (en) | 2020-12-03 | 2020-12-03 | Digital earth surface model house DLG automatic extraction method based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011400508.2A CN112419384B (en) | 2020-12-03 | 2020-12-03 | Digital earth surface model house DLG automatic extraction method based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112419384A CN112419384A (en) | 2021-02-26 |
CN112419384B true CN112419384B (en) | 2023-06-09 |
Family
ID=74829939
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011400508.2A Active CN112419384B (en) | 2020-12-03 | 2020-12-03 | Digital earth surface model house DLG automatic extraction method based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112419384B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113393450B (en) * | 2021-06-25 | 2023-04-07 | 杭州今奥信息科技股份有限公司 | Data quality inspection method and system for digital line drawing and readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101281034A (en) * | 2008-05-16 | 2008-10-08 | 南京师范大学 | Building single image three-dimensional measurement method based on space right-angle relationship |
JP2008253362A (en) * | 2007-04-02 | 2008-10-23 | Taito Corp | Game image generation method in remote radio control type online match game system |
CN101836233A (en) * | 2007-10-30 | 2010-09-15 | 株式会社博思科 | House movement determining method, house movement determining program, house movement determining image generating method, and house movement determining image |
CN106600680A (en) * | 2015-10-20 | 2017-04-26 | 星际空间(天津)科技发展有限公司 | Batch type refined three-dimensional modeling method of building frame model |
CN110570428A (en) * | 2019-08-09 | 2019-12-13 | 浙江合信地理信息技术有限公司 | method and system for segmenting roof surface patch of building from large-scale image dense matching point cloud |
CN111322994A (en) * | 2020-04-22 | 2020-06-23 | 福州市勘测院 | Large-scale cadastral survey method for intensive house area based on unmanned aerial vehicle oblique photography |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7578109B2 (en) * | 2004-08-31 | 2009-08-25 | Gossamer Space Frames | Space frames and connection node arrangement for them |
-
2020
- 2020-12-03 CN CN202011400508.2A patent/CN112419384B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008253362A (en) * | 2007-04-02 | 2008-10-23 | Taito Corp | Game image generation method in remote radio control type online match game system |
CN101836233A (en) * | 2007-10-30 | 2010-09-15 | 株式会社博思科 | House movement determining method, house movement determining program, house movement determining image generating method, and house movement determining image |
CN101281034A (en) * | 2008-05-16 | 2008-10-08 | 南京师范大学 | Building single image three-dimensional measurement method based on space right-angle relationship |
CN106600680A (en) * | 2015-10-20 | 2017-04-26 | 星际空间(天津)科技发展有限公司 | Batch type refined three-dimensional modeling method of building frame model |
CN110570428A (en) * | 2019-08-09 | 2019-12-13 | 浙江合信地理信息技术有限公司 | method and system for segmenting roof surface patch of building from large-scale image dense matching point cloud |
CN111322994A (en) * | 2020-04-22 | 2020-06-23 | 福州市勘测院 | Large-scale cadastral survey method for intensive house area based on unmanned aerial vehicle oblique photography |
Non-Patent Citations (2)
Title |
---|
Y. Yin 等.A vectorization method of building edge based on high resolution DSM data.《2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)》.2016,1572-1574. * |
陈良浩 等.基于DSM点云纠正的正射影像房屋边缘锯齿消除.《测绘科学技术学报》.2017,第34卷(第03期),279-282. * |
Also Published As
Publication number | Publication date |
---|---|
CN112419384A (en) | 2021-02-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103017739B (en) | Manufacturing method of true digital ortho map (TDOM) based on light detection and ranging (LiDAR) point cloud and aerial image | |
CN109242862B (en) | Real-time digital surface model generation method | |
CN112598796B (en) | Method for constructing and automatically updating three-dimensional building information model based on generalized point cloud | |
CN106199558A (en) | Barrier method for quick | |
CN110852347A (en) | Fire detection method using improved YOLO v3 | |
CN103729846B (en) | LiDAR point cloud data edge detection method based on triangular irregular network | |
CN114219819A (en) | Oblique photography model unitization method based on orthoscopic image boundary detection | |
CN107833273B (en) | Oblique photography three-dimensional model objectification application method based on three-dimensional simulation model | |
CN103927731A (en) | Low-altitude remote sensing image rapid and automatic splicing method without POS assisting | |
CN102708587A (en) | Method and system for acquiring three-dimensional building information rapidly | |
CN104157011A (en) | Modeling method for three-dimensional terrain | |
CN112419384B (en) | Digital earth surface model house DLG automatic extraction method based on artificial intelligence | |
CN114004938A (en) | Urban scene reconstruction method and device based on mass data | |
CN113325389A (en) | Unmanned vehicle laser radar positioning method, system and storage medium | |
CN105184854A (en) | Quick modeling method for cloud achievement data of underground space scanning point | |
CN111915720B (en) | Automatic conversion method from building Mesh model to CityGML model | |
CN111982077B (en) | Electronic map drawing method and system and electronic equipment | |
Zhao et al. | A 3D modeling method for buildings based on LiDAR point cloud and DLG | |
CN116524382A (en) | Bridge swivel closure accuracy inspection method system and equipment | |
CN114004740B (en) | Building wall line extraction method based on unmanned aerial vehicle laser radar point cloud | |
CN112348950B (en) | Topological map node generation method based on laser point cloud distribution characteristics | |
CN114463494A (en) | Automatic topographic feature line extracting algorithm | |
Kim et al. | Data simulation of an airborne lidar system | |
Yao et al. | Automatic extraction method study of road marking lines based on projection of point clouds | |
Lafarge et al. | Modeling urban landscapes from point clouds: a generic approach |
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 |