CN108171720A - A kind of oblique photograph model object frontier probe method based on geometrical statistic information - Google Patents
A kind of oblique photograph model object frontier probe method based on geometrical statistic information Download PDFInfo
- Publication number
- CN108171720A CN108171720A CN201810026437.0A CN201810026437A CN108171720A CN 108171720 A CN108171720 A CN 108171720A CN 201810026437 A CN201810026437 A CN 201810026437A CN 108171720 A CN108171720 A CN 108171720A
- Authority
- CN
- China
- Prior art keywords
- cloud
- boundary
- point cloud
- information
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000000523 sample Substances 0.000 title claims abstract description 13
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012946 outsourcing Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing 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
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to a kind of oblique photograph model object frontier probe method based on geometrical statistic information, including obtaining the point cloud information of model;A cloud is screened;It is projected to cloud is put after screening in unified plane, obtains statistical information of the cloud based on a certain plane;Statistical filtering is carried out to cloud, noise at the boundary is reduced, obtains the boundary characteristic of more obvious object;Cut-point cloud is obtained with noisy standalone object;The point cloud data for meeting object bounds feature is filtered out, the point for obtaining meeting object actual boundary feature converges conjunction;The boundary point cloud information of objects of statistics, obtains the boundary vector of a cloud;Using obtained vector closure boundary, model is split, obtains independent editable object.The present invention in the case of no manual intervention, can extract the boundary information of building object and based on this realization object singulation, be greatly improved efficiency, the further application for oblique photograph data provides technical support.
Description
Technical field
The invention belongs to city three-dimensional model data fine-grained management and application field, be related to object fine-grained management with it is right
As the crucial application scenarios such as identification, more particularly to a kind of oblique photograph model object frontier probe based on geometrical statistic information
Method.
Background technology
During cybercity construction of today, oblique photograph technology platform is as a kind of advanced data acquisition and builds
Mould technology can realize good three-dimensional reconstruction while high-precision atural object spatial information is provided.But existing inclination
Photography model adds texture mapping to form by a continuous irregular triangle network, it is impossible to be drawn according to different geographical entities
It is divided into the different geographic objects that can individually choose, this results in oblique photograph model there was only function of browse and can not complete to geography
The editorial management of factor data, this brings great challenge to the further in-depth analysis application of data." singulation " refers to
Each we want the geographic object individually managed, be one by one individually, can be with selected entity.It realizes and clicks, looks into
GIS basic functions, the realizations of " singulation " such as inquiry greatly facilitate effect to the popularization and application of oblique photograph technology.
In current research, realize oblique photograph data singulation scheme be mainly based upon it is manual or automanual
Method.Wherein, it is mainly the boundary line by manual delineation building object based on pure manual method, with obtained object
Vector edges bound pair building is split;It is mainly to add in vector base map based on automanual Object Segmentation thinking, and vector bottom
Figure is also what is obtained by manual vector quantization, and judge that algorithm obtains the region of target object based on manual polygonal region.
Therefore, the most important shortcoming efficiency of existing method is too low, and human cost is too high, can not apply on a large scale.
Invention content
For as mentioned above the problem of, the present invention proposes a kind of oblique photograph model object side based on geometrical statistic information
Boundary's detection method, realizes the detection of object bounds, and be partitioned into can individually-edited management building object, greatly improve
The utilization ratio of model.
In order to achieve the above object, technical solution provided by the invention is that a kind of inclination based on geometrical statistic information is taken the photograph
Shadow model object frontier probe method, includes the following steps:
Step 1, the point cloud information of model is obtained;
Step 2, a cloud is screened;
Step 3, cloud will be put after screening to project in unified plane, obtain statistical information of the cloud based on a certain plane;
Step 4, statistical filtering is carried out to cloud, reduces noise at the boundary, obtain the boundary characteristic of more obvious object;
Step 5, cut-point cloud is obtained with noisy standalone object;
Step 6, the point cloud data for meeting object bounds feature is filtered out, obtains the point cloud for meeting object actual boundary feature
Set;
Step 7, the boundary point cloud information of objects of statistics, obtains the boundary vector of a cloud;
Step 8, using obtained vector closure boundary, model is split, obtains independent editable object.
Further, the specific implementation of step 2 is the point cloud filtered out approximately perpendicular to corresponding to tri patch,
Retained, remove other clouds.
Further, the specific implementation of step 4 is that, using the statistical filtering algorithm based on cloud density, will study
Regional network is formatted, and counts the quantity fallen at each grid midpoint, given threshold, filters out the area that cloud density is less than threshold value
Domain obtains the boundary characteristic of more obvious object.
Further, it is used in step 5 based on multiple dimensioned cloud cluster segmentation algorithm cut-point cloud, given threshold, it will be away from
It separates, obtains with noisy standalone object from scene from the point cloud less than threshold range.
Further, stochastical sampling consistency algorithm detection of straight lines is combined in step 6 and detects camber line, screening with Hough transformation
Go out to meet the straightway of building object bounds feature and arc segment point cloud data.
Further, using the minimum outsourcing rectangle of object as boundary vector in step 7.
Further, the specific implementation of step 8 is to ask friendship based on the subject area that vector boundary is formed and model,
Selection belongs to the point cloud data of existing object region, three-dimensional object surface is rebuild according to obtained point cloud data, with reference to original
Textures data in beginning model file obtain independent editable building object to new model pinup picture.
Compared with prior art, it is an advantage of the invention that:The present invention realizes the oblique photograph based on geometrical statistic information
Model object frontier probe is divided with model, realizes the function of automated border detection, compares with for conventional method, substantially carrying
Efficiency has been risen, has realized automated border detection and object singulation.The object that can be individually-edited obtained can be oblique photograph
The further application of model provides data basis;The method based on geometrical statistic information proposed in scheme can be in certain noise
The real border of building object is obtained in allowed band;The multiple dimensioned cluster segmentation algorithm based on Euclidean distance is fine in scheme
Avoid the shortcomings that single scale clustering method can not be applied with entire scenario objects, unified scene originally is subdivided into can
With individually operated object, the object singulation further to become more meticulous eliminates a large amount of noise spot cloud, and it is more accurate to obtain
Building boundary.This programme in the case of no manual intervention, can extract the boundary information of building object and be based on
This realizes object singulation, is greatly improved efficiency, and the further application for oblique photograph data provides technical support.
Description of the drawings
Fig. 1 is flow chart of the embodiment of the present invention;
Fig. 2 is statistical information figure of the point cloud of the embodiment of the present invention based on a certain plane;
Fig. 3 is point cloud statistical filtering result figure of the embodiment of the present invention;
Fig. 4 is that multiple dimensioned cloud cluster result figure is based in the embodiment of the present invention;
Fig. 5 is single object bounds point cloud hum pattern in the embodiment of the present invention;
Fig. 6 is the object bounds point cloud hum pattern after Hough transformation in the embodiment of the present invention;
Fig. 7 is the approximate boundaries schematic vector diagram of object in the embodiment of the present invention, and the dotted line in figure is outer for the minimum of object
Packet rectangle;
Fig. 8,9,10 are the different side schematic views carried out in the embodiment of the present invention for segmentation result after textures.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, with reference to the accompanying drawings and examples to the present invention
Technical solution be described further.
(1) the point cloud information of model is obtained
It is object-based multi-view image collection in the building process of oblique photograph data model, according to parallax, meter
Calculate and restore the spatial information (i.e. point cloud data) of object;In order to obtain the original point cloud of data, this programme deeply parses original
The point cloud information of data, and it is stored as editable cloud file.
(2) according to the method phasor of model data intermediate cam dough sheet, a cloud is screened
In view of in model the characteristics of object bounds, in order to which interference information is further removed, Scheme Choice combination triangle
The normal information screening point cloud of dough sheet, only retains approximately perpendicular to the point cloud corresponding to tri patch, the purpose for the arrangement is that
Retain wall point cloud.
(3) cloud is projected in unified plane, obtains statistical information of the cloud based on a certain plane
In order to further visualize wall point cloud statistical information, a cloud is projected in unified plane, obtained by Scheme Choice
Effect as shown in Figure 2, it can be seen that the boundary characteristic of object is obvious, is exactly in next step that design method is further gone
Except noise spot cloud.
(4) with reference to Euclidean distance, statistical filtering is carried out to cloud, reduces noise at the boundary
By step (3) result it is known that in the place that building and ground have a common boundary point cloud accumulation, point cloud density compares
Greatly, and in other regions, the density ratio for putting cloud is relatively low, and the present embodiment is close using the point cloud mentioned in bibliography [1] as a result,
The statistical filtering algorithm of degree by survey region gridding, and counts the quantity fallen at each grid midpoint, given threshold, filtering
Fall the sparse region of a cloud, obtain the boundary characteristic of more obvious object, the results are shown in Figure 3;
[1] Li Renzhong, Yang Man, Ran Yuan open slowly, and Jing Junfeng, Li Peng flies point cloud denoisings of the based on method base and simplifies calculation
Method [J] laser and optoelectronics are in progress, 2018,55 (01):011008,DOI:10.3788/lop55.011008.
(5) the multiple dimensioned clustering algorithm based on Euclidean distance, cut-point cloud are obtained with noisy independent object
Based on point cloud data as above, the object that all sharpness of border are obtained on unified scale be it is highly difficult,
Then, using based on multiple dimensioned cloud cluster segmentation algorithm.
On the experimental basis of previous step, therefore characteristics of objects clearly selects the point cloud based on Euclidean distance
Cluster segmentation, when the distance between cloud is within a certain threshold value of setting, then it represents that the otherwise point cloud genera belongs in same category
Different classifications, can be independent by the object in given scenario by strategy as above, as shown in Figure 4.For inhomogeneity
Other object sets different distance thresholds and can separate object from scene, and the target object in the present embodiment is builds
Object is built, the results are shown in Figure 5;
(6) camber line is detected with reference to stochastical sampling consistency algorithm (RANSAC) detection of straight lines and Hough transformation, further sieved
The point cloud data for meeting building boundary characteristic (straightway and arc segment) is selected, removes object bounds noise, obtains satisfaction pair
As the point of actual boundary feature converges conjunction.
The result of the test that step (5) obtains is not sufficient to the real border of expression object, and also there are many boundaries in data
The accuracy of influence of noise object bounds identification.It can be obtained by priori, the boundary of building is mainly by line segment, camber line
It is composed, then passes through the filtering of design straight line and camber line filtering algorithm, a cloud noise is filtered, the results showed that, it obtains
To object bounds substantially conform to true object bounds information, as shown in Figure 6;
(7) the boundary point cloud information of objects of statistics, obtains the approximate boundaries vector of a cloud
The object detection task being referred from two dimensional image, this programme are detected using minimum outsourcing rectangle come approximate representative
Scene in building object.In the Detection task of building, what is taken is that a cloud is projected to a certain plane, as a result,
The minimum outsourcing rectangle of drafting is also completed on that plane, obtains that the results are shown in Figure 7;
(8) the vector closure boundary arrived utilized, is split model, obtains independent object
After a complete standalone object is found, in order to which object is independent from entire environment, so as to
In further processing and application later, the method with reference to described in bibliography [2], the subject area formed based on vector boundary
Friendship is asked with model, selection belongs to the point cloud data of existing object region, and three dimensional object is rebuild according to obtained point cloud data
Surface (TIN), with reference to the textures data in archetype file to new model pinup picture, the obtained editable building of independence
Object, the different side schematic view effects after textures are as seen in figs. 8-10;
[2] threedimensional model monomerization approach research [J] computer works of Wang Yong, Hao Xiaoyan, the Li Ying based on oblique photograph
Journey and application, 2017, DOI:10.3778/j.issn.1002-8331.1608-0458.
Specific embodiment described herein is only an example for the spirit of the invention.Technology belonging to the present invention is led
The technical staff in domain can do various modifications or additions to described specific embodiment or replace in a similar way
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (7)
- A kind of 1. oblique photograph model object frontier probe method based on geometrical statistic information, which is characterized in that including as follows Step:Step 1, the point cloud information of model is obtained;Step 2, a cloud is screened;Step 3, cloud will be put after screening to project in unified plane, obtain statistical information of the cloud based on a certain plane;Step 4, statistical filtering is carried out to cloud, reduces noise at the boundary, obtain the boundary characteristic of more obvious object;Step 5, cut-point cloud is obtained with noisy standalone object;Step 6, the point cloud data for meeting object bounds feature is filtered out, the point for obtaining meeting object actual boundary feature converges It closes;Step 7, the boundary point cloud information of objects of statistics, obtains the boundary vector of a cloud;Step 8, using obtained vector closure boundary, model is split, obtains independent editable object.
- 2. a kind of oblique photograph model object frontier probe method based on geometrical statistic information as described in claim 1, It is characterized in that:The specific implementation of step 2 is the point cloud filtered out approximately perpendicular to corresponding to tri patch, is retained, Remove other clouds.
- 3. a kind of oblique photograph model object frontier probe method based on geometrical statistic information as described in claim 1, It is characterized in that:The specific implementation of step 4 is, using the statistical filtering algorithm based on cloud density, by survey region grid Change, and count the quantity fallen at each grid midpoint, given threshold filters out the region that cloud density is less than threshold value, obtains more Add the boundary characteristic of apparent object.
- 4. a kind of oblique photograph model object frontier probe method based on geometrical statistic information as described in claim 1, It is characterized in that:It is used in step 5 based on multiple dimensioned cloud cluster segmentation algorithm cut-point cloud, given threshold will be apart from less than threshold The point cloud of value range is separated from scene, is obtained with noisy standalone object.
- 5. a kind of oblique photograph model object frontier probe method based on geometrical statistic information as described in claim 1, It is characterized in that:Stochastical sampling consistency algorithm detection of straight lines is combined in step 6 and detects camber line with Hough transformation, filters out to meet and build Build the straightway of object object bounds feature and arc segment point cloud data.
- 6. a kind of oblique photograph model object frontier probe method based on geometrical statistic information as described in claim 1, It is characterized in that:Using the minimum outsourcing rectangle of object as boundary vector in step 7.
- 7. a kind of oblique photograph model object frontier probe method based on geometrical statistic information as described in claim 1, It is characterized in that:The specific implementation of step 8 is to ask friendship based on the subject area that vector boundary is formed and model, selection belongs to The point cloud data of existing object region rebuilds three-dimensional object surface according to obtained point cloud data, with reference to archetype text Textures data in part obtain independent editable building object to new model pinup picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810026437.0A CN108171720A (en) | 2018-01-08 | 2018-01-08 | A kind of oblique photograph model object frontier probe method based on geometrical statistic information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810026437.0A CN108171720A (en) | 2018-01-08 | 2018-01-08 | A kind of oblique photograph model object frontier probe method based on geometrical statistic information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108171720A true CN108171720A (en) | 2018-06-15 |
Family
ID=62517972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810026437.0A Pending CN108171720A (en) | 2018-01-08 | 2018-01-08 | A kind of oblique photograph model object frontier probe method based on geometrical statistic information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108171720A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109766404A (en) * | 2019-02-12 | 2019-05-17 | 湖北亿咖通科技有限公司 | Points cloud processing method, apparatus and computer readable storage medium |
CN110110621A (en) * | 2019-04-23 | 2019-08-09 | 安徽大学 | The oblique photograph point cloud classifications method of deep learning model is integrated based on multiple features |
CN110189405A (en) * | 2019-05-31 | 2019-08-30 | 重庆市勘测院 | A kind of outdoor scene three-dimensional modeling method for taking building density into account |
CN110379004A (en) * | 2019-07-22 | 2019-10-25 | 泰瑞数创科技(北京)有限公司 | The method that a kind of pair of oblique photograph achievement carries out terrain classification and singulation is extracted |
CN110866531A (en) * | 2019-10-15 | 2020-03-06 | 深圳新视达视讯工程有限公司 | Building feature extraction method and system based on three-dimensional modeling and storage medium |
CN111288985A (en) * | 2020-03-04 | 2020-06-16 | 北京易控智驾科技有限公司 | Map determination method and device, equipment and automatic mine car driving method |
CN111612806A (en) * | 2020-01-10 | 2020-09-01 | 江西理工大学 | Building facade window extraction method and device |
CN111815701A (en) * | 2020-06-11 | 2020-10-23 | 吉旗物联科技(上海)有限公司 | Volume determination method and device based on rectangular column projection points |
CN111833286A (en) * | 2019-03-26 | 2020-10-27 | 深圳中科飞测科技有限公司 | Point cloud processing method and system, detection method and system and readable medium |
CN112163251A (en) * | 2020-08-24 | 2021-01-01 | 北京航空航天大学 | Building model unitization method and device, storage medium and electronic equipment |
WO2021000241A1 (en) * | 2019-07-01 | 2021-01-07 | Oppo广东移动通信有限公司 | Point cloud model reconstruction method, encoder, decoder, and storage medium |
CN112700531A (en) * | 2020-12-18 | 2021-04-23 | 武汉大学 | Building tilt model layered household display method fused with vector household diagram |
WO2022166323A1 (en) * | 2021-02-03 | 2022-08-11 | 华为技术有限公司 | Method for determining road line, and related apparatus and device |
CN116051980A (en) * | 2022-12-13 | 2023-05-02 | 北京乾图科技有限公司 | Building identification method, system, electronic equipment and medium based on oblique photography |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009087367A1 (en) * | 2008-01-08 | 2009-07-16 | Gmj Design Ltd | A method of creating a representation of the surface of an object |
CN101726255A (en) * | 2008-10-24 | 2010-06-09 | 中国科学院光电研究院 | Method for extracting interesting buildings from three-dimensional laser point cloud data |
CN106846494A (en) * | 2017-01-16 | 2017-06-13 | 青岛海大新星软件咨询有限公司 | Oblique photograph three-dimensional building thing model automatic single-body algorithm |
-
2018
- 2018-01-08 CN CN201810026437.0A patent/CN108171720A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009087367A1 (en) * | 2008-01-08 | 2009-07-16 | Gmj Design Ltd | A method of creating a representation of the surface of an object |
CN101726255A (en) * | 2008-10-24 | 2010-06-09 | 中国科学院光电研究院 | Method for extracting interesting buildings from three-dimensional laser point cloud data |
CN106846494A (en) * | 2017-01-16 | 2017-06-13 | 青岛海大新星软件咨询有限公司 | Oblique photograph three-dimensional building thing model automatic single-body algorithm |
Non-Patent Citations (1)
Title |
---|
杨存英: "基于倾斜影像的建筑物提取与参数化三维重建", 《中国优秀硕士学位论文全文数据库 基础科学辑(月刊)》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109766404A (en) * | 2019-02-12 | 2019-05-17 | 湖北亿咖通科技有限公司 | Points cloud processing method, apparatus and computer readable storage medium |
CN111833286A (en) * | 2019-03-26 | 2020-10-27 | 深圳中科飞测科技有限公司 | Point cloud processing method and system, detection method and system and readable medium |
CN110110621A (en) * | 2019-04-23 | 2019-08-09 | 安徽大学 | The oblique photograph point cloud classifications method of deep learning model is integrated based on multiple features |
CN110189405A (en) * | 2019-05-31 | 2019-08-30 | 重庆市勘测院 | A kind of outdoor scene three-dimensional modeling method for taking building density into account |
CN110189405B (en) * | 2019-05-31 | 2023-05-23 | 重庆市勘测院 | Live-action three-dimensional modeling method considering building density |
US11790563B2 (en) | 2019-07-01 | 2023-10-17 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Point cloud model reconstruction method, encoder, and decoder |
WO2021000241A1 (en) * | 2019-07-01 | 2021-01-07 | Oppo广东移动通信有限公司 | Point cloud model reconstruction method, encoder, decoder, and storage medium |
CN110379004A (en) * | 2019-07-22 | 2019-10-25 | 泰瑞数创科技(北京)有限公司 | The method that a kind of pair of oblique photograph achievement carries out terrain classification and singulation is extracted |
CN110866531A (en) * | 2019-10-15 | 2020-03-06 | 深圳新视达视讯工程有限公司 | Building feature extraction method and system based on three-dimensional modeling and storage medium |
CN111612806A (en) * | 2020-01-10 | 2020-09-01 | 江西理工大学 | Building facade window extraction method and device |
CN111288985A (en) * | 2020-03-04 | 2020-06-16 | 北京易控智驾科技有限公司 | Map determination method and device, equipment and automatic mine car driving method |
CN111815701A (en) * | 2020-06-11 | 2020-10-23 | 吉旗物联科技(上海)有限公司 | Volume determination method and device based on rectangular column projection points |
CN112163251A (en) * | 2020-08-24 | 2021-01-01 | 北京航空航天大学 | Building model unitization method and device, storage medium and electronic equipment |
CN112700531A (en) * | 2020-12-18 | 2021-04-23 | 武汉大学 | Building tilt model layered household display method fused with vector household diagram |
WO2022166323A1 (en) * | 2021-02-03 | 2022-08-11 | 华为技术有限公司 | Method for determining road line, and related apparatus and device |
CN116051980A (en) * | 2022-12-13 | 2023-05-02 | 北京乾图科技有限公司 | Building identification method, system, electronic equipment and medium based on oblique photography |
CN116051980B (en) * | 2022-12-13 | 2024-02-09 | 北京乾图科技有限公司 | Building identification method, system, electronic equipment and medium based on oblique photography |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108171720A (en) | A kind of oblique photograph model object frontier probe method based on geometrical statistic information | |
CN110363858B (en) | Three-dimensional face reconstruction method and system | |
CN109993783B (en) | Roof and side surface optimization reconstruction method for complex three-dimensional building point cloud | |
CN111508074B (en) | Three-dimensional building model simplification method based on roof contour line | |
CN112070769B (en) | Layered point cloud segmentation method based on DBSCAN | |
CN104134234B (en) | A kind of full automatic three-dimensional scene construction method based on single image | |
CN105844064B (en) | The semi-automatic method for reconstructing of three-dimensional transformer substation based on laser point cloud data | |
CN105572687B (en) | A kind of method that building digital adventure appearance is made based on mobile lidar point cloud | |
CN103679807B (en) | A kind of dispersion point cloud reconstructing method of band boundary constraint | |
CN114332366B (en) | Digital urban single house point cloud elevation 3D feature extraction method | |
CN109900338B (en) | Method and device for measuring volume of pavement pit | |
CN109242862B (en) | Real-time digital surface model generation method | |
CN105303616B (en) | Embossment modeling method based on single photo | |
CN103870845A (en) | Novel K value optimization method in point cloud clustering denoising process | |
CN103701466A (en) | Scattered point cloud compression algorithm based on feature reservation | |
CN105139379B (en) | Based on the progressive extracting method of classified and layered airborne Lidar points cloud building top surface | |
CN110379004A (en) | The method that a kind of pair of oblique photograph achievement carries out terrain classification and singulation is extracted | |
CN109712143A (en) | A kind of Fast image segmentation method based on super-pixel multiple features fusion | |
CN108986024A (en) | A kind of regularly arranged processing method of laser point cloud based on grid | |
CN110827408A (en) | Real-time three-dimensional reconstruction method based on depth sensor | |
CN110653166B (en) | Fruit detection and classification method and device | |
CN110348067B (en) | Method, system, medium and equipment for extracting physical parameters of airflow characterization | |
CN106683105A (en) | Image segmentation method and image segmentation device | |
CN110211078B (en) | Significance detection method based on anisotropic diffusion | |
CN110648406A (en) | Tooth-gum fast segmentation algorithm of invisible tooth socket |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |
|
RJ01 | Rejection of invention patent application after publication |