CN114119902A - Building extraction method based on unmanned aerial vehicle inclined three-dimensional model - Google Patents
Building extraction method based on unmanned aerial vehicle inclined three-dimensional model Download PDFInfo
- Publication number
- CN114119902A CN114119902A CN202111394175.1A CN202111394175A CN114119902A CN 114119902 A CN114119902 A CN 114119902A CN 202111394175 A CN202111394175 A CN 202111394175A CN 114119902 A CN114119902 A CN 114119902A
- Authority
- CN
- China
- Prior art keywords
- building
- point cloud
- cloud data
- dimensional model
- aerial vehicle
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a building extraction method based on an unmanned aerial vehicle inclined three-dimensional model, which comprises the following steps: step 1: firstly, acquiring a high-precision real-scene three-dimensional image and forming a three-dimensional model by utilizing unmanned aerial vehicle oblique photogrammetry; step 2: classifying and filtering the point cloud data; and step 3: carrying out image conversion on the classified and filtered point cloud data; and 4, step 4: deleting the building wall surface composition nodes and reserving the building main body top surface composition nodes; and 5: connecting the rest main body nodes in the step 4 end to end and forming a building characteristic outline; step 6: and (5) overlapping and reducing the building characteristic contour in the step (5) in a coordinate system of the three-dimensional model, and finally obtaining the contour of the target building. The method has high automation degree, the whole process can be completed only by one person, the extracted building has high precision and low cost, and the technical problem that the existing building cannot be in an inclined three-dimensional scene can be solved.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle inclination three-dimensional models, and particularly relates to a building extraction method based on an unmanned aerial vehicle inclination three-dimensional model.
Background
With the continuous development of computer technology and low-altitude inclined three-dimensional system platform technology, a brand-new method for acquiring three-dimensional reconstruction of urban scenes appears: oblique three-dimensional photography; the oblique photography is that a plurality of sensors are carried on the same aircraft platform, images are collected from five different angles such as one vertical angle, four oblique angles and the like, the three-dimensional structure of a target object is recovered based on a three-dimensional modeling method of multi-view images, and meanwhile, the surface texture information of a three-dimensional model is obtained. In recent years, with the increasing maturity of unmanned aerial vehicle technology, the cost of acquiring aerial image data is also greatly reduced. Therefore, the construction of urban three-dimensional scenes based on multi-view oblique images becomes more extensive.
The existing building outline extraction method based on the aerial image of the common unmanned aerial vehicle comprises the steps of generating three-dimensional point cloud by using a space-three combined dense matching method, filtering the point cloud, and detecting a building from the point cloud. And after the wall surface of the detected building is deleted, extracting the rough outline of the building from the top surface information of the building. And (3) on the building rough contour serving as a buffer area overlapped and spliced image, utilizing the building rough contour as shape prior information, and carrying out evolution in the buffer area by using a level set algorithm to finally obtain the building contour.
The building precision that prior art obtained through the mode that ordinary unmanned aerial vehicle aerial photograph image drawed the building profile is low, has reduced the precision that the building profile was drawed to be difficult for using widely.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a building extraction method based on an unmanned aerial vehicle inclined three-dimensional model, which can obtain a high-precision three-dimensional model and then extract high-precision building contour information, and the method improves the precision of building contour extraction; the invention solves the problems that the information precision of the image obtained by the existing method for extracting the outline of the building is low, and the precision of extracting the outline of the building is reduced, so that the method is not easy to popularize.
In order to achieve the purpose, the invention adopts the technical scheme that:
a building extraction method based on an unmanned aerial vehicle inclined three-dimensional model comprises the following steps:
step 1: firstly, acquiring a high-precision live-action three-dimensional image by utilizing unmanned aerial vehicle oblique photogrammetry, forming a live-action three-dimensional model through processing, then automatically extracting point cloud data of a building outline according to the live-action three-dimensional model, giving the point cloud data to a coordinate system, and cutting the point cloud data with coordinates into a plurality of small slices;
step two 2: classifying and filtering interference sundries in the point cloud data obtained in the step 1, wherein the interference sundries comprise trees, water bodies and cables, and finally obtaining the point cloud data of the building;
and step 3: carrying out image conversion on the classified and filtered building point cloud data, converting all the point cloud data obtained in the step 2 into images one by one, and obtaining an image corresponding to each slice;
and 4, step 4: deleting the building wall surface composition nodes and the highest points and the lowest points of the bulges or the depressions on the top surface of the building; reserving the top surface of the building main body to form a node;
and 5: connecting the building body nodes reserved in the step 4 end to end and forming a building characteristic outline;
step 6: and (5) overlapping and reducing the building characteristic contour in the step (5) in a coordinate system of the three-dimensional model, and finally obtaining the contour of the target building.
In the step 1, a coordinate system is given to the point cloud data: firstly, defining three directions of a building as length (X), width (Y) and height (Z) respectively, and carrying out a plurality of slicing treatments on the building in the three directions respectively; respectively connecting points in three directions of each small slice; and correspondingly processing the small slice connecting points on each surface of the building to finally obtain the point cloud data of the building.
The step 2 adopts a uniform sampling filtering mode, firstly, a seed grid is constructed, and critical points of buildings and interference impurities are marked into a plurality of seed points; and then, point cloud data is extracted, and when the extracted seed points coincide with the point positions of the building in the process of lifting the point cloud data, the point cloud is automatically shielded by a filtering algorithm, otherwise, the point cloud data is regarded as the building point cloud data.
Deleting the wall surface of the building by adopting a partition method in the steps 3, 4, 5 and 6; connecting the point cloud data by adopting a jump type connecting method; and beautifying the finally extracted building outline.
Compared with the prior art, the invention has the following beneficial effects:
the method has the advantages that the automation degree is high, a large amount of manual intervention is not needed, the whole process can be completed only by one person, the building extracted by the method is high in precision and low in cost, and the technical problem that the existing building cannot be in an inclined three-dimensional scene can be solved.
Drawings
Fig. 1 is a flowchart of a building extraction method based on an unmanned aerial vehicle inclined three-dimensional model according to an embodiment of the present invention.
Fig. 2 is a diagram of a live-action three-dimensional model.
Fig. 3 is a sectional view of a live-action three-dimensional model.
Fig. 4 is a building roof profile.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the following further describes in detail a building extraction method based on an unmanned aerial vehicle tilted three-dimensional model by using an implementation case and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the invention provides a building extraction method based on an unmanned aerial vehicle inclined three-dimensional model, comprising the following steps:
step 1: firstly, a high-precision live-action three-dimensional image obtained by oblique photogrammetry of an unmanned aerial vehicle is utilized to form a live-action three-dimensional model; the high precision three-dimensional image processing generation is shown in fig. 2.
Step 2: and classifying and filtering the point cloud data.
And step 3: and (4) carrying out image conversion on the classified and filtered point cloud data, and finally generating a real-scene three-dimensional model tangent plane diagram as shown in fig. 3.
And 4, step 4: and deleting the building wall surface composition nodes and reserving the building main body top surface composition nodes.
And 5: and (4) connecting the rest body nodes in the step (4) end to end and forming a building characteristic outline.
Step 6: and (5) overlapping and reducing the building characteristic contour in the step (5) in a coordinate system of the three-dimensional model, and finally obtaining the contour of the target building. Finally, the contour diagram of the top surface of the building shown in fig. 4 is obtained.
The embodiments in the above description can be further combined or replaced, and the embodiments are only described as preferred examples of the present invention, and do not limit the concept and scope of the present invention, and various changes and modifications made to the technical solution of the present invention by those skilled in the art without departing from the design concept of the present invention belong to the protection scope of the present invention. The scope of the invention is given by the appended claims and any equivalents thereof.
Claims (4)
1. A building extraction method based on an unmanned aerial vehicle inclined three-dimensional model is characterized by comprising the following steps:
step 1: firstly, acquiring a high-precision live-action three-dimensional image by utilizing unmanned aerial vehicle oblique photogrammetry, forming a live-action three-dimensional model through processing, then automatically extracting point cloud data of a building outline according to the live-action three-dimensional model, giving the point cloud data to a coordinate system, and cutting the point cloud data with coordinates into a plurality of small slices;
step two 2: classifying and filtering interference sundries in the point cloud data obtained in the step 1, wherein the interference sundries comprise trees, water bodies and cables, and finally obtaining the point cloud data of the building;
and step 3: carrying out image conversion on the classified and filtered building point cloud data, converting all the point cloud data obtained in the step 2 into images one by one, and obtaining an image corresponding to each slice;
and 4, step 4: deleting the building wall surface composition nodes and the highest points and the lowest points of the bulges or the depressions on the top surface of the building; reserving the top surface of the building main body to form a node;
and 5: connecting the building body nodes reserved in the step 4 end to end and forming a building characteristic outline;
step 6: and (5) overlapping and reducing the building characteristic contour in the step (5) in a coordinate system of the three-dimensional model, and finally obtaining the contour of the target building.
2. The building extraction method based on the unmanned aerial vehicle inclined three-dimensional model as claimed in claim 1, wherein: in the step 1, a coordinate system is given to the point cloud data: firstly, defining three directions of a building as length (X), width (Y) and height (Z) respectively, and carrying out a plurality of slicing treatments on the building in the three directions respectively; respectively connecting points in three directions of each small slice; and correspondingly processing the small slice connecting points on each surface of the building to finally obtain the point cloud data of the building.
3. The building extraction method based on the unmanned aerial vehicle inclined three-dimensional model as claimed in claim 1, wherein: the step 2 adopts a uniform sampling filtering mode, firstly, a seed grid is constructed, and critical points of buildings and interference impurities are marked into a plurality of seed points; and then, point cloud data is extracted, and when the extracted seed points coincide with the point positions of the building in the process of lifting the point cloud data, the point cloud is automatically shielded by a filtering algorithm, otherwise, the point cloud data is regarded as the building point cloud data.
4. The building extraction method based on the unmanned aerial vehicle inclined three-dimensional model as claimed in claim 1, wherein: deleting the wall surface of the building by adopting a partition method in the steps 3, 4, 5 and 6; connecting the point cloud data by adopting a jump type connecting method; and beautifying the finally extracted building outline.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111394175.1A CN114119902A (en) | 2021-11-23 | 2021-11-23 | Building extraction method based on unmanned aerial vehicle inclined three-dimensional model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111394175.1A CN114119902A (en) | 2021-11-23 | 2021-11-23 | Building extraction method based on unmanned aerial vehicle inclined three-dimensional model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114119902A true CN114119902A (en) | 2022-03-01 |
Family
ID=80440086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111394175.1A Pending CN114119902A (en) | 2021-11-23 | 2021-11-23 | Building extraction method based on unmanned aerial vehicle inclined three-dimensional model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114119902A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926602A (en) * | 2022-04-13 | 2022-08-19 | 湖北省国土测绘院 | Building single-body method and system based on three-dimensional point cloud |
| CN115019007A (en) * | 2022-08-05 | 2022-09-06 | 烟台市地理信息中心 | Three-dimensional model making method and system based on unmanned aerial vehicle intelligent air route planning |
| CN117272491A (en) * | 2023-11-21 | 2023-12-22 | 广东广宇科技发展有限公司 | Rapid modeling method, equipment and medium based on AI drawing model |
-
2021
- 2021-11-23 CN CN202111394175.1A patent/CN114119902A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926602A (en) * | 2022-04-13 | 2022-08-19 | 湖北省国土测绘院 | Building single-body method and system based on three-dimensional point cloud |
| CN114926602B (en) * | 2022-04-13 | 2023-03-31 | 湖北省国土测绘院 | Building singleization method and system based on three-dimensional point cloud |
| CN115019007A (en) * | 2022-08-05 | 2022-09-06 | 烟台市地理信息中心 | Three-dimensional model making method and system based on unmanned aerial vehicle intelligent air route planning |
| CN117272491A (en) * | 2023-11-21 | 2023-12-22 | 广东广宇科技发展有限公司 | Rapid modeling method, equipment and medium based on AI drawing model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717983B (en) | Building elevation three-dimensional reconstruction method based on knapsack type three-dimensional laser point cloud data | |
| CN112595258B (en) | Ground object contour extraction method based on ground laser point cloud | |
| CN112070769B (en) | Layered point cloud segmentation method based on DBSCAN | |
| CN114119902A (en) | Building extraction method based on unmanned aerial vehicle inclined three-dimensional model | |
| CN105354883B (en) | The quick subtle three-dimensional modeling methods of 3ds Max and system based on a cloud | |
| CN109242862B (en) | Real-time digital surface model generation method | |
| CN106815847A (en) | Trees dividing method and single tree extracting method based on laser radar point cloud | |
| CN107680168B (en) | Grid simplifying method based on plane fitting in three-dimensional reconstruction | |
| CN114332366A (en) | Digital city single house point cloud facade 3D feature extraction method | |
| CN114612488A (en) | Building-integrated information extraction method, computer device, and storage medium | |
| CN106504277A (en) | A kind of improved ICP points cloud autoegistration method | |
| CN111784840B (en) | LOD (line-of-sight) level three-dimensional data singulation method and system based on vector data automatic segmentation | |
| CN108765568A (en) | A kind of multi-level building quick three-dimensional reconstructing method based on laser radar point cloud | |
| CN109816664A (en) | A kind of three-dimensional point cloud dividing method and device | |
| CN113192200B (en) | Method for constructing urban real scene three-dimensional model based on space-three parallel computing algorithm | |
| KR101549155B1 (en) | Method of automatic extraction of building boundary from lidar data | |
| CN115564926B (en) | Three-dimensional patch model construction method based on image building structure learning | |
| CN104751479A (en) | Building extraction method and device based on TIN data | |
| Hu et al. | A fast and simple method of building detection from LiDAR data based on scan line analysis | |
| CN114332134A (en) | Building facade extraction method and device based on dense point cloud | |
| CN116071530B (en) | Building roof voxelized segmentation method based on airborne laser point cloud | |
| CN114549956A (en) | Deep learning assisted inclined model building facade target recognition method | |
| CN116721228B (en) | Building elevation extraction method and system based on low-density point cloud | |
| CN116051980B (en) | Building identification method, system, electronic equipment and medium based on oblique photography | |
| CN115661398A (en) | Building extraction method, device and equipment for live-action three-dimensional model |
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 |