CN113822914A - Method for unifying oblique photography measurement model, computer device, product and medium - Google Patents
Method for unifying oblique photography measurement model, computer device, product and medium Download PDFInfo
- Publication number
- CN113822914A CN113822914A CN202111068825.3A CN202111068825A CN113822914A CN 113822914 A CN113822914 A CN 113822914A CN 202111068825 A CN202111068825 A CN 202111068825A CN 113822914 A CN113822914 A CN 113822914A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- model
- vector
- pixel
- cloud data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method for unitizing an oblique photogrammetry model, a computer device, a product and a medium, which are used for collecting pixel-level point cloud data which is output while the oblique model is produced and is completely registered with a geographic coordinate system of the oblique model; extracting a point cloud set of interest objects in the pixel-level point cloud data; carrying out automatic vector wrapping on the point cloud set of each interest object to obtain an external contour vector of the interest object; and superposing the initially produced tilt model and the outer contour vector of the interest object to form a singleton result of the tilt model. The method realizes the acquisition of the single vector data by using the pixel point cloud, has less manual investment, high efficiency and low cost, and can greatly improve the application prospect of the tilt model data.
Description
Technical Field
The invention relates to a model dynamic singleization technology, in particular to a method for acquiring vector data required by dynamic singleization by AI identification aiming at pixel point cloud data produced in an inclined mode.
Background
The model monomer refers to each object needing to be managed separately, and is an individual entity which can be selected. Only with the ability to be singletized can the data be managed, not just viewed. For manual modeling, singleton is a self-evident matter. That is, in the process of artificial modeling, objects (such as buildings, street lamps, trees, etc.) needing to be managed separately are naturally made into separate models and are also separated from other objects. The existing oblique photography modeling algorithm is only a three-dimensional real-scene model construction, and does not include distinguishing ground objects such as buildings, the ground, trees and the like, a continuous Tin network is constructed, the whole area is still three-dimensional map data with uneven and continuous fluctuation in nature, and ground surface objects in the data cannot be independently selected, operated and managed, namely, each interested object cannot be materialized or objectified. Therefore, the related attributes of the surface feature object cannot be connected to the single entity object, and GIS operations such as attribute query, space query, thematic map making and the like cannot be implemented, so that the three-dimensional data is 'good-looking' and 'useless', and the value and the practicability of the model data are reduced.
At present, the main methods of the monomer process are mainly divided into three categories: vector cutting singulation, ID singulation, and dynamic singulation. The vector cutting and singulation is the most intuitive idea, namely, the oblique photography model is cut by using corresponding vector surfaces of buildings, roads, trees and the like, and a continuous triangular net is physically divided to realize the singulation. The method can really segment the connected models in a physical sense and then manage and operate the segmented models. The ID singleization is to store the ID value of the corresponding vector plane by using the extra storage space of each vertex in the triangular patch; that is, all the vertexes of the triangular patch corresponding to a building store the same ID value, so that when the building is selected by the mouse, the building can show a highlight effect. The dynamic individuation is to provide the practical expression and operation experience of the similar individuation for the user by utilizing the two-dimensional vector plane matched with the photographic object, so that the objective expression and operation are realized, and a two-three-dimensional integrated channel between the oblique photographic model and the two-dimensional vector plane is opened.
The above three mainstream oblique photography model singulation methods are all manual processing of a certain workload on a model, for example, to obtain a vector in a singulation process in dynamic singulation, the model needs to be used for extracting a manual vector first, and the work needs to invest more labor and cost in a region with complex construction and large engineering quantity, so that the work is not practical and large-scale operation production, and thus, an efficient singulation mode is also an important factor influencing large-scale later application of the oblique model.
For the automatic modeling of oblique photography, the modeling process is as follows: firstly, carrying out aerial triangulation on original image data to generate dense matching point cloud, then carrying out thinning on the point cloud, then constructing a triangulation network to form a white membrane, and finally mapping and attaching texture pictures to the texture to generate an oblique photography live-action model, wherein the process has no manual intervention link. However, the conventional laser point cloud data must be acquired by the laser radar alone, and cannot be acquired simultaneously with the oblique unmanned aerial vehicle camera in the field work for acquiring the oblique image, the matching and calculation process of the point cloud and the image is complex in the field work data processing, and when most of the laser radars acquire the laser point cloud, the original point cloud data is free of RGB channel data, and when AI identification point cloud classification is performed, identification and extraction are performed through conditions such as point cloud density, structure and mutual relation.
The theoretical density of airborne laser point cloud can be infinite, but for practical projects, the density of the laser point cloud is generally distributed discretely from a few to dozens of points in a square meter measuring area range, the density is small, the color information of the non-covered area is not abundant, and the feature extraction and identification are difficult. Meanwhile, errors exist in the point cloud coloring process, so that the process of utilizing laser point cloud data to conduct singulation is complex and high in cost. .
At present, the vectors of dynamic singleization in the industry are obtained by utilizing a produced inclined live-action model according to a manual mapping mode to obtain DLG two-dimensional vector lines or planes, and the DLG two-dimensional vector lines or planes are registered with the inclined model to realize the dynamic singleization result. However, as the oblique photogrammetry three-dimensional modeling becomes more mature, the specification is gradually improved, the market business is increased day by day, and the efficiency is the most concerned aspect in the monomer process. The majority of the existing monomer methods are realized by manual methods, and have the advantages of low efficiency, high cost and low feasibility of large-scale and large-scale data. Meanwhile, in the existing artificial intelligence recognition algorithm, the algorithm for recognizing and calculating the three-dimensional laser point cloud is more, and the recognition algorithm for OSGB data with strong oblique model encapsulation is not mature.
Disclosure of Invention
The invention aims to solve the technical problem that aiming at the defects of the prior art, the invention provides a method, a computer device, a product and a medium for unitizing an oblique photogrammetry model, and improves the unitizing efficiency and the accuracy of the unitizing result.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a method for unitizing a oblique photogrammetry model comprises the following steps:
s1, collecting pixel-level point cloud data which are output while the tilt model is produced and are completely registered with the tilt model geographic coordinate system;
s2, extracting a point cloud set of interest objects in the pixel-level point cloud data;
s3, automatically wrapping the point cloud set of each interest object by using a vector to obtain an external contour vector of the interest object;
and S4, superposing the initially produced tilt model and the external contour vector of the interest object to form a singleton result of the tilt model.
Due to the fact that the same original data, the same calculation process and the same control system are adopted, the pixel-level point cloud data which are completely registered with the model geographic coordinate system, namely the pixel-level point cloud model, can be output while the inclined model is produced. Compared with laser point clouds, the pixel point clouds have richer information in non-covered areas than the laser point clouds, and can be subjected to coordinate registration with the inclined model without complex calculation processing, so that the segmentation and extraction accuracy and efficiency of the conventional AI identification algorithm are improved by utilizing the pixel point clouds. The density of the pixel point cloud is the precision of the original resolution of the inclined image, the precision is basically centimeter-level, the pixel-level point cloud is produced while the model is produced, field acquisition and interior processing are avoided, the RGB channel data of the pixel point cloud is the original RGB channel data of real image pixels, and color-endowing processing is not needed, therefore, the vector extraction of the pixel point cloud for inclination singularization can be completely matched with the geographical coordinates of the inclined model, and the pixel point cloud has richer color information than the laser point cloud data, the precision of an AI (artificial intelligence) identification extraction algorithm can be greatly improved, the calculation complexity is reduced, and the singularization efficiency is greatly improved.
In order to further improve the accuracy of the singulation process, step S1 further includes: preprocessing the pixel-level point cloud data to obtain preprocessed pixel-level point cloud data; then, step S2 is replaced with:
and S2, extracting a point cloud set of the interest object in the preprocessed pixel-level point cloud data.
In step S2, the interest objects include one or more of buildings, roads, and plots.
In step S3, the outer contour vector of the object of interest is one of a vector line, a vector plane, and a vector volume. Because the pixel point cloud data is generated through the production process of the tilt model, the coordinates of the pixel point cloud data and the coordinates of the pixel point cloud data are completely matched, and the vector data is obtained according to the pixel point cloud, the obtained vector data can be perfectly integrated into the tilt model, and further the accurate registration monomer result is obtained.
And outputting the pixel-level point cloud data in a form that a point cloud coordinate has three channels of RGB. The pixel point cloud comprises basic data characteristics of the point cloud, each point is provided with RGB three-primary color channel information, more characteristic information is provided, the production process of the pixel point cloud is a process for producing an inclined live-action model based on an inclined image, redundant field data acquisition requirements and excessive field data processing processes are avoided, and the pixel point cloud data matched in a ratio of 1:1 can be produced based on the calculation result while the live-action model is produced. Therefore, the existing AI point cloud identification and extraction algorithm is used for carrying out extraction, segmentation and other processing on the pixel point cloud, so that the AI identification accuracy can be improved, the field acquisition and field data processing processes of the laser point cloud are avoided, and the monomer efficiency is improved.
In the invention, the density of the pixel-level point cloud data is between 400 points/square meter and 1200 points/square meter, so that the accuracy and the identification efficiency of the AI identification algorithm are further improved.
As one inventive concept, the present invention provides a computer apparatus comprising a memory, a processor, and a computer program stored on the memory; the processor executes the computer program to implement the steps of the method of the present invention.
As an inventive concept, the present invention also provides a computer-readable storage medium having stored thereon a computer program/instructions; wherein the computer program/instructions, when executed by a processor, performs the steps of the method of the present invention.
As an inventive concept, the present invention also provides a computer program product comprising computer programs/instructions; wherein the computer program/instructions, when executed by a processor, performs the steps of the method of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
1. the method utilizes the pixel point cloud data to perform AI identification and extraction, obtains vector data required by the singularization of the tilt model, and superposes the obtained vector file and the tilt model to realize the singularization process of the tilt model. . The invention creatively carries out intelligent identification on the three-dimensional pixel point cloud data, which not only can greatly improve the efficiency of the traditional manual monomer method, but also can ensure the accuracy of AI identification results, thereby ensuring that the monomer results can be widely popularized and applied;
2. the produced tilt model is used for manually measuring the results of monomer area, coordinates and the like as real values, and the real values and the monomer results of the method are used as calculated values for comparison test. The experiment identifies, segments and extracts houses, dry farmlands, paddy fields, forests and roads, the extraction accuracy rate of the houses reaches more than 95%, and the statistical error of the single-span house roof area is within 3% compared with the result of an oblique photography model; the identification and segmentation accuracy of the paddy field and the dry field reaches more than 92%, and the area statistical error is within 5%; compared with the traditional AI laser point cloud identification method and the traditional manual monomer method, the method saves the processing processes of field acquisition and field laser point cloud, and obviously improves the efficiency;
3. when the vector extraction is carried out, the direct identification Of the achievement Of the tilt model is avoided, because the tilt model is an encapsulation model with an LOD (level Of details) hierarchical format OSGB (open Scene graph binary), the identification and extraction must be carried out aiming at the complex LOD, the conventional AI algorithm has no better basis, the dynamic and monomer conversion Of the model requires vector data registered with the model, and the vector data can be obtained from the point cloud or the model, so that the pixel point cloud data which is simultaneously output by the model and is completely matched is identified, the basis Of the conventional AI point cloud identification and segmentation extraction algorithm can be utilized, meanwhile, the research and development Of the identification algorithm for the model format with strong encapsulation performance are not required, and the cost is greatly saved;
4. the invention carries out artificial intelligent recognition and cutting on the pixel point cloud data produced by the inclined model under the same condition to obtain a single vector, does not need to change a recognition algorithm, and greatly reduces the realization difficulty. Meanwhile, the pixel point cloud and the model are completely registered, so that the vector obtained by identification can be completely registered with the model, thereby realizing the high-efficiency automatic singleization result and increasing the popularization and application of the oblique photogrammetry three-dimensional model.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
FIG. 2 is a three-dimensional pixel point cloud data (with RGB channels) output during oblique photogrammetry model production;
FIG. 3 shows a building, a forest land, a road, and a plot partitioned by the AI recognition partitioning algorithm;
FIGS. 3-1 and 3-2 are identified house objects;
FIGS. 3-3 and 3-4 are identified woodland objects;
FIGS. 3-5 and 3-6 are identified road objects;
FIGS. 3-7 and 3-8 are identified arable land objects;
FIG. 4 is a diagram for identifying and segmenting point cloud data of similar pixels to form clusters or vectors;
FIG. 5 the tilt model is superimposed with the vector to form a singulation result.
Detailed Description
Referring to fig. 1, an automated method for unitizing a oblique photogrammetry model according to an embodiment of the present invention includes the following steps:
a, outputting pixel point cloud data under the same coordinate system by utilizing original oblique image data while producing an oblique model, outputting the pixel point cloud in a form of point cloud coordinate with RGB (red, green and blue) three channels according to the original pixel density, and performing conventional denoising and thinning treatment to obtain a result;
b, recognizing, segmenting and extracting the pixel point cloud data in the step A by utilizing an AI recognition segmentation algorithm, and extracting a point cloud set of interest objects such as house buildings, roads, plots and the like;
step C, carrying out automatic vector wrapping on the point cloud collection object which is identified and extracted to form a vector surface, a line and a body, and replacing the building or the structure in the geometric sense with a vector to obtain a required projection vector surface, a required projection vector line and a required projection vector body;
and D, superposing the initially produced tilt model and the vector in the step C, and mapping the initially produced tilt model in a GIS platform to form a single result of the tilt model so as to carry out subsequent application.
The core of the embodiment of the invention is to creatively utilize the pixel point cloud to replace the laser point cloud to carry out monomer identification and extraction, and meanwhile, an AI algorithm does not need to be separately developed aiming at the complicated LOD level of the tilt model OSGB, so the identification efficiency and the identification precision can be simultaneously improved.
In the embodiment of the invention, the object of the AI identification segmentation algorithm is the three-dimensional pixel point cloud data with RGB channels generated in the step A, the pixel point cloud is also point data which is uniformly distributed in an aggregation manner, the AI identification algorithm of the data is more mature (such as pointent, pointent + +, randLA, DBSCAN and the like), and simultaneously, each point has RGB three primary color channel information, so that more characteristic information is provided, and the AI identification accuracy can be improved.
In the embodiment of the invention, the vector data is the external contour vector of each interest object after the pixel point cloud AI is identified and segmented. Because the pixel point cloud data is generated in the production process of the tilt model, the coordinates of the pixel point cloud data and the coordinates of the pixel point cloud data are completely matched, and the vector data is obtained according to the pixel point cloud, the obtained vector data can be perfectly integrated into the tilt model, a precise registration monomer result is formed, and finally data application is carried out.
Fig. 2-5 reflect the automatic identification and singulation process of the tilt model AI according to the present invention, which respectively represent the produced three-dimensional pixel point cloud data, the cut individual objects identified by the pixel point cloud AI, the clusters or vectors formed by the same type of pixel point cloud data after identification and segmentation, the singulation result formed by superimposing the tilt model and the vectors, and the technical route flow chart of the method according to the present invention. FIG. 2 shows pixel point cloud data generated while an oblique model is being produced in a project area, where the point cloud density is equivalent to the image density and has RGB information of pixels; FIG. 3 shows the result of the object extracted by the method of the present invention, wherein every two small graphs are a group of categories, which are buildings, forest lands, roads, and cultivated land blocks in turn; FIG. 4 is a result obtained by aggregating all the results after the extraction of the recognition object is completed by the method of the present invention, so as to put the result into the model for overall inspection; FIG. 5 shows the results of the present invention with monomers that have been highlighted in different colors to differentiate expression. The result of the data test by the method of the invention can be known as follows: when the targets such as houses, plots, roads and the like are segmented and extracted, vector range lines of the identified and extracted vector planes are surrounded into a surface area, the area of the surface area is compared with a projection area measured on the inclined model, and an error is found to be within a range of 1% -3%.
Claims (9)
1. A method for unitizing a oblique photogrammetry model is characterized by comprising the following steps:
s1, collecting pixel-level point cloud data which are output while the tilt model is produced and are completely registered with the tilt model geographic coordinate system;
s2, extracting a point cloud set of interest objects in the pixel-level point cloud data;
s3, automatically wrapping the point cloud set of each interest object by using a vector to obtain an external contour vector of the interest object;
and S4, superposing the initially produced tilt model and the external contour vector of the interest object to form a singleton result of the tilt model.
2. The method for unitizing oblique photogrammetry model according to claim 1, wherein step S1 further comprises: preprocessing the pixel-level point cloud data to obtain preprocessed pixel-level point cloud data; then, step S2 is replaced with:
and S2, extracting a point cloud set of the interest object in the preprocessed pixel-level point cloud data.
3. The oblique photogrammetry model singulation method of claim 1, wherein in step S2, the object of interest comprises one or more of a house building, a road, and a parcel.
4. The oblique photogrammetry model unitization method of claim 1, wherein in step S3, the external contour vector of the object of interest is one of a vector line, a vector plane and a vector volume.
5. The method for unitizing oblique photogrammetry model according to one of claims 1 to 4, wherein the pixel-level point cloud data is output in a form of point cloud coordinates with three channels of RGB.
6. The method of claim 1 to 4, wherein the density of the pixel-level point cloud data is 400-1200 dots/m.
7. A computer apparatus comprising a memory, a processor and a computer program stored on the memory; characterized in that the processor executes the computer program to carry out the steps of the method according to one of claims 1 to 6.
8. A computer readable storage medium having stored thereon a computer program/instructions; characterized in that the computer program/instructions, when executed by a processor, implement the steps of the method of one of claims 1 to 6.
9. A computer program product comprising a computer program/instructions; characterized in that the computer program/instructions, when executed by a processor, performs the steps of the method according to one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111068825.3A CN113822914A (en) | 2021-09-13 | 2021-09-13 | Method for unifying oblique photography measurement model, computer device, product and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111068825.3A CN113822914A (en) | 2021-09-13 | 2021-09-13 | Method for unifying oblique photography measurement model, computer device, product and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113822914A true CN113822914A (en) | 2021-12-21 |
Family
ID=78914425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111068825.3A Pending CN113822914A (en) | 2021-09-13 | 2021-09-13 | Method for unifying oblique photography measurement model, computer device, product and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822914A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114557640A (en) * | 2022-02-21 | 2022-05-31 | 广州宝乐软件科技有限公司 | Cleaning robot and data processing method and device thereof |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107452061A (en) * | 2017-06-28 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | Generation method, device, equipment and the computer-readable recording medium of building model based on oblique photograph technology |
| JP2019008571A (en) * | 2017-06-26 | 2019-01-17 | 株式会社デンソーアイティーラボラトリ | Object recognition device, object recognition method, program, and trained model |
| CN111462275A (en) * | 2019-01-22 | 2020-07-28 | 北京京东尚科信息技术有限公司 | Map production method and device based on laser point cloud |
| CN111932671A (en) * | 2020-08-22 | 2020-11-13 | 扆亮海 | Three-dimensional solid model reconstruction method based on dense point cloud data |
| CN112927370A (en) * | 2021-02-25 | 2021-06-08 | 苍穹数码技术股份有限公司 | Three-dimensional building model construction method and device, electronic equipment and storage medium |
| CN113111787A (en) * | 2021-04-15 | 2021-07-13 | 北京沃东天骏信息技术有限公司 | Target detection method, device, equipment and storage medium |
| US20210278544A1 (en) * | 2018-04-23 | 2021-09-09 | Blackmore Sensors & Analytics, LLC. | Lidar system for autonomous vehicle |
-
2021
- 2021-09-13 CN CN202111068825.3A patent/CN113822914A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| JP2019008571A (en) * | 2017-06-26 | 2019-01-17 | 株式会社デンソーアイティーラボラトリ | Object recognition device, object recognition method, program, and trained model |
| CN107452061A (en) * | 2017-06-28 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | Generation method, device, equipment and the computer-readable recording medium of building model based on oblique photograph technology |
| US20210278544A1 (en) * | 2018-04-23 | 2021-09-09 | Blackmore Sensors & Analytics, LLC. | Lidar system for autonomous vehicle |
| CN111462275A (en) * | 2019-01-22 | 2020-07-28 | 北京京东尚科信息技术有限公司 | Map production method and device based on laser point cloud |
| CN111932671A (en) * | 2020-08-22 | 2020-11-13 | 扆亮海 | Three-dimensional solid model reconstruction method based on dense point cloud data |
| CN112927370A (en) * | 2021-02-25 | 2021-06-08 | 苍穹数码技术股份有限公司 | Three-dimensional building model construction method and device, electronic equipment and storage medium |
| CN113111787A (en) * | 2021-04-15 | 2021-07-13 | 北京沃东天骏信息技术有限公司 | Target detection method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 郭如宝 郝利娟 刘旭东 刘军 刘尧晖 张炜: ""基于倾斜摄影的实景三维单体化模型构建方法"", 《测绘通报》, pages 1 - 1 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114557640A (en) * | 2022-02-21 | 2022-05-31 | 广州宝乐软件科技有限公司 | Cleaning robot and data processing method and device thereof |
| CN114557640B (en) * | 2022-02-21 | 2023-08-01 | 广州宝乐软件科技有限公司 | Data processing method and device of cleaning robot and cleaning robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113128405B (en) | Plant identification and model construction method combining semantic segmentation and point cloud processing | |
| AU2020103026A4 (en) | A Single Tree Crown Segmentation Algorithm Based on Super-pixels and Topological Features in Aerial Images | |
| CN113034689B (en) | Laser point cloud-based terrain three-dimensional model, terrain map construction method and system, and storage medium | |
| US11995886B2 (en) | Large-scale environment-modeling with geometric optimization | |
| CN109242862B (en) | Real-time digital surface model generation method | |
| US11763522B2 (en) | 3D reconstruction method based on on-site edge-cloud collaboration for cultivated land | |
| CN111815776A (en) | Three-dimensional building fine geometric reconstruction method integrating airborne and vehicle-mounted three-dimensional laser point clouds and streetscape images | |
| KR101165534B1 (en) | Geospatial modeling system providing simulated tree trunks and branches for groups of tree crown vegetation points and related methods | |
| CN108734728A (en) | A kind of extraterrestrial target three-dimensional reconstruction method based on high-resolution sequence image | |
| CN116310192A (en) | Urban building three-dimensional model monomer reconstruction method based on point cloud | |
| CN111047695B (en) | Method for extracting height spatial information and contour line of urban group | |
| CN107833273B (en) | Oblique photography three-dimensional model objectification application method based on three-dimensional simulation model | |
| CN114612488A (en) | Building-integrated information extraction method, computer device, and storage medium | |
| CN114998536A (en) | Model generation method and device based on novel basic mapping and storage medium | |
| CN111754618B (en) | Object-oriented live-action three-dimensional model multi-level interpretation method and system | |
| CN111598048A (en) | Urban village-in-village identification method integrating high-resolution remote sensing image and street view image | |
| CN114119863A (en) | Method for automatically extracting street tree target and forest attribute thereof based on vehicle-mounted laser radar data | |
| CN113362359A (en) | Building automatic extraction method of oblique photography data fused with height and spectrum information | |
| CN109492606A (en) | Multispectral vector picture capturing method and system, three dimensional monolithic method and system | |
| CN112241661A (en) | Urban ground feature fine classification method combining airborne LiDAR point cloud data and aerial image | |
| CN115049925A (en) | Method for extracting field ridge, electronic device and storage medium | |
| CN115468917A (en) | Method and system for extracting crop information of farmland plot based on high-resolution remote sensing | |
| CN114820975A (en) | Three-dimensional scene simulation reconstruction system and method based on all-element parameter symbolization | |
| CN113822914A (en) | Method for unifying oblique photography measurement model, computer device, product and medium | |
| Xu et al. | Fast and accurate registration of large scene vehicle-borne laser point clouds based on road marking information |
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 |