CN116934976A - RGBD-based light-weight ancient architecture scene scanning and reconstructing method - Google Patents

RGBD-based light-weight ancient architecture scene scanning and reconstructing method Download PDF

Info

Publication number
CN116934976A
CN116934976A CN202310959549.2A CN202310959549A CN116934976A CN 116934976 A CN116934976 A CN 116934976A CN 202310959549 A CN202310959549 A CN 202310959549A CN 116934976 A CN116934976 A CN 116934976A
Authority
CN
China
Prior art keywords
scanning
rgbd
historic building
height
ancient
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
Application number
CN202310959549.2A
Other languages
Chinese (zh)
Inventor
徐凌玉
徐阳
饶梓妍
高文彬
赵文慧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jiaotong University
Original Assignee
Beijing Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Jiaotong University filed Critical Beijing Jiaotong University
Priority to CN202310959549.2A priority Critical patent/CN116934976A/en
Publication of CN116934976A publication Critical patent/CN116934976A/en
Pending legal-status Critical Current

Links

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Physiology (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Strategic Management (AREA)
  • Computer Graphics (AREA)
  • Development Economics (AREA)
  • Genetics & Genomics (AREA)
  • Game Theory and Decision Science (AREA)
  • Geometry (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention discloses a light-weight historic building scene scanning and reconstructing method based on RGBD, which comprises the following steps: adjusting and fixing the height and angle of the RGBD camera according to the elevation height of the ancient building to be scanned and the maximum visual field range of the RGBD camera; determining a scanning range and an area of an ancient building to be collected, and dividing a scanning area; determining a scanning path according to the shape and the size of each divided scanning area, and converting the scanning path into a path scheme; performing depth image data acquisition by using an RGBD camera according to a planned path scheme to obtain a time sequence data packet; and carrying out continuous frame point cloud conversion and adjacent frame matching on the obtained time sequence data packet to obtain the ancient building scene model. The method is based on the RGBD camera to collect depth map data and RGB image data of the surface of the ancient building in a hand-held and portable mode in a short distance, and can realize scanning and three-dimensional model reconstruction of the ancient building in a near-real-time dynamic environment. The method has the advantages of low acquisition cost and small limitation on acquisition environment, and can be applied to the modeling of the ancient architecture in a large scale.

Description

RGBD-based light-weight ancient architecture scene scanning and reconstructing method
Technical Field
The invention relates to the technical field of urban updating and heritage protection, in particular to a light-weight ancient architecture scene scanning and reconstructing method based on RGBD.
Background
The ancient architecture scene scanning and reconstruction technology has great significance in the aspects of historical research, cultural heritage protection, architectural design, transformation, travel popularization and the like: the three-dimensional scanning technology of the ancient architecture can help a historical researcher to better know the structure and the structure of the ancient architecture, so that the historical and cultural value of the ancient architecture can be better researched. For the ancient architecture which is damaged or is gradually damaged, the three-dimensional scanning technology can comprehensively record and protect the ancient architecture, so that the cultural value of the ancient architecture is saved. The three-dimensional scanning technology of the ancient architecture can provide basic data of architectural design and reconstruction schemes, and can provide more design inspiration for architects and designers. For ancient architecture with important cultural value, the three-dimensional scanning technology can produce more real and vivid virtual tourism scenes, and provides better display effect for tourism popularization. In a word, it not only can protect and preserve the ancient architecture, but also can provide more research and design data for the personnel in the relevant field, drive the development of relevant industry.
The current site ancient architecture scene scanning and reconstruction mainly adopts the following two modes:
1. total station: and (5) registering the point clouds (Point Cloud Registration), namely splicing the point clouds and registering the point clouds, and for the point clouds with overlapping information of two frames, transforming the overlapping part of the point clouds under the same unified coordinate system by solving a transformation matrix (a rotation matrix R and a translation matrix T). However, the complete scene and the three-dimensional point cloud model of the target to be registered are difficult to obtain in the actual scene, and huge data volume of the point cloud brings great calculation amount to registration, so that the positioning method based on the point cloud registration is difficult to apply in actual engineering. Total stations are a high precision instrument that requires advanced technology and precision components to ensure accuracy and precision of measurement results, which makes the total station relatively expensive and requires a large amount of capital to purchase and maintain. Second, total stations have limitations in terms of acquisition environment, and total stations are often required to make measurements on relatively flat and stable ground, as uneven terrain or unstable ground can affect the accuracy of the instrument, and weather conditions such as heavy winds, rain, snow, etc. can also affect the accuracy of the measurement results. In addition, the measurement using the total station requires a certain skill and experience. Operators need to receive specialized training to ensure proper instrumentation and accurate data acquisition, and specialized skills and software are required for data processing and analysis, which also increases cost and time investment.
2. Oblique photography: image registration (Image registration) is a process of matching and overlapping two or more images acquired at different times, with different sensors (imaging devices) or under different conditions (weather, illuminance, imaging position and angle, etc.), and has been widely used in the fields of remote sensing data analysis, computer vision, image processing, etc. The process of the process registration technique is as follows: firstly, extracting features of two images to obtain feature points; finding matched characteristic point pairs by carrying out similarity measurement; then obtaining image space coordinate transformation parameters through the matched characteristic point pairs; and finally, registering the images by the coordinate transformation parameters. However, in practical application, larger computing resources are consumed, and practical use is difficult; tilt photography requires specialized equipment and techniques such as tilt cameras, accurate GPS positioning systems, and high precision ground control points, which require high capital investment. Moreover, oblique photography requires a large amount of data processing and calculation, requires the use of specialized software and computers, and also requires specialized talents, which require high costs. Moreover, oblique photography requires stringent requirements on the acquisition environment, and some environmental factors can affect data acquisition, such as weather, light, obstructions, and the like. If adverse environmental conditions are met, the acquisition effect is affected, and the data quality is difficult to guarantee. Moreover, oblique photography requires planning and layout of the acquisition area, finding the suitable location and angle for the photography, and this is more difficult if the acquisition area is large.
The high cost of its own sensors and computing resources, as well as the limitations on the acquisition environment, make it difficult to apply them in mass-scale in ancient building modeling, whether it be total or oblique photography.
Disclosure of Invention
The invention aims to provide a light-weight ancient architecture scene scanning and reconstructing method based on RGBD aiming at the technical defects that the sensor cost and the calculation resource cost are high and the acquisition environment is limited in the prior art. The method is based on an RGBD camera, and the depth map data and RGB image data of the surface of the ancient building are acquired in a hand-held portable mode in a short distance, so that the ancient building is scanned and the three-dimensional model is reconstructed in a near-real-time dynamic environment.
Another object of the present invention is to provide a lightweight ancient architecture scene scanning and reconstruction system based on RGBD.
It is another object of the present invention to provide a computer readable storage medium.
The technical scheme adopted for realizing the purpose of the invention is as follows:
RGBD-based light-weight ancient architecture scene scanning and reconstruction method comprises the following steps:
step 1: adjusting and fixing the height and angle of the RGBD camera according to the elevation height of the ancient building to be scanned and the maximum visual field range of the RGBD camera; the ancient building to be scanned comprises a single building and a building group;
step 2: estimating the size of the ancient building to be collected, and dividing a scanning area by combining the surrounding environment;
step 3: determining a scanning path according to the shape and the size of each scanning area divided in the step 2, and converting the scanning path into a path scheme;
step 4: performing depth image data acquisition by using an RGBD camera according to the path scheme planned in the step 3, and obtaining a time sequence data packet;
step 5: and carrying out continuous frame point cloud conversion and adjacent frame matching on the obtained time sequence data packet to obtain the ancient building scene model.
In the above technical solution, the elevation of the ancient building to be scanned includes all the parts from the ground to the roof.
In the above technical scheme, under the height and angle of the RGBD camera fixed in step 1, the single scanning height of the RGBD camera is greater than the elevation height of the ancient building to be scanned.
In the technical scheme, when the elevation height of the ancient building to be scanned is larger than 8 meters, the complete elevation data are acquired by adopting a mode of repeated scanning and splicing.
In the above technical scheme, in step 2, firstly, the dimensions of the ancient architecture to be collected, including length, width, height and geometric shapes of each part, are estimated, and a reference is provided for dividing a scanning area by combining the cruising ability of the scanning equipment;
then, surrounding roads, squares and buildings are also brought into the scanning range so as to ensure the integrity of the scanning result;
and finally, dividing the whole scanning range into a plurality of small areas according to the field condition and the parameters and the cruising ability of the scanning equipment so as to scan each area respectively.
In the above technical solution, in step 3, a genetic algorithm or simulated annealing is used to optimize the scan path.
In the above technical solution, the time-series data packet includes a depth image, acceleration data, and a time stamp.
In the above technical solution, in step 5, continuous frame point cloud conversion and adjacent frame matching are performed on the obtained time-series data packet according to the RTAB-MAP type computer vision algorithm.
In another aspect of the present invention, an RGBD-based lightweight historic building scene scanning and reconstruction system includes an interconnected RGBD camera, a microprocessor and a memory, the microprocessor being programmed or configured to perform the steps of the lightweight historic building scene scanning and reconstruction method described above.
In another aspect of the present invention, a computer readable storage medium has a computer program stored therein for programming or configuring by a microprocessor to perform the steps of the lightweight historic building scene scanning and reconstruction method described above.
Compared with the prior art, the invention has the beneficial effects that:
according to the RGBD-based ancient architecture scene scanning and reconstructing method provided by the invention, the RGBD camera is used for acquiring the depth map data and the RGB image data of the ancient architecture surface in a handheld and portable manner in a short distance, so that the ancient architecture can be scanned and reconstructed in a three-dimensional model in a near-real-time dynamic environment. The method has the advantages of low acquisition cost and small limitation on acquisition environment, and can be applied to the modeling of the ancient architecture in a large scale.
Drawings
FIG. 1 is a general flow of a lightweight RGBD historic building scene scanning and reconstruction method and system;
fig. 2 is a schematic diagram of the division of the ancient architecture scanning area to be collected in the step 2;
FIG. 3 is a schematic illustration of planning a historic building area acquisition route setup;
FIG. 4 shows the effect of the point cloud model example of the historic building component after the time series data is synthesized;
FIG. 5 shows the effect of the model example of the ancient architecture scene point cloud after the time series data synthesis;
fig. 6 shows an effect of a model example of the depression point cloud of the ancient architecture after the synthesis of the time series data.
Detailed Description
The present invention will be described in further detail with reference to specific examples. 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.
Example 1
RGBD-based light-weight ancient architecture scene scanning and reconstruction method comprises the following steps:
step 1: adjusting and fixing the height and angle of the RGBD camera according to the elevation height of the ancient building to be scanned and the maximum visual field range of the RGBD camera;
the height and shape of the building need to be considered in scanning to determine the optimal scanning position and angle in order to obtain the most accurate data. Under fixed height and angle, the elevation height of single scanning of the camera is larger than the elevation height of the ancient building to be scanned, and the calculation formula is as follows:
h＝d·tan(θ/2) (1)
where h is the elevation height of a single scan, the scan distance d is the distance of the scanning device from the building surface, and the scan angle θ is the rotation angle of the scanning device in the horizontal direction. When the elevation height of the ancient building to be scanned is larger than 8 meters, the complete elevation data is acquired by adopting a mode of multi-time scanning and splicing when the elevation height of the single scanning of the camera is insufficient to cover the elevation height of the ancient building to be scanned. And calculating a vertical face height calculation formula of multi-scanning splicing:
H＝n·h (2)
wherein n is the number of splicing times, and the elevation height h of single scanning can be calculated by a formula (1).
The elevation height of the ancient building to be scanned comprises all parts from the ground to the roof, including wall surfaces, windows, doors, eave, roofs and the like.
The maximum field of view FOV (Field of View) of the RGBD camera, denoted (fv, fh), where V and H represent the maximum fields of view (in degrees) in the vertical and horizontal directions, respectively.
Step 2: the dimension of the ancient building or building group to be collected is estimated, wherein the dimension comprises the length, the width, the height and the geometric shapes of all parts, and the dimension is combined with the cruising ability of the scanning equipment to provide a reference for dividing the scanning area. Secondly, the surrounding environment is examined, whether the scanning operation is feasible for the surrounding environment and the terrain while the building is scanned is considered, and the surrounding roads, squares and the building are required to be also included in the scanning range so as to ensure the integrity of the scanning result. And finally dividing a scanning area, and dividing the whole scanning range into a plurality of small areas according to the field condition, the parameters and the cruising ability of the scanning equipment so as to scan each area respectively. Generally, if a single building, the scanning area may be divided according to different parts and structural features of the building, such as front, back, interior, exterior, etc. of the building; in the case of a building group, control points may be provided around or within the building group while the building group is split into individual buildings for scanning. The control points are used for registering data of different scanning positions so as to ensure that the scanning data of the whole building group are in the same coordinate system and can be correctly spliced into a complete three-dimensional model.
Step 3: and (3) determining a scanning path according to the shape and the size of each scanning area divided in the step (2), and converting the scanning path into a path scheme. In general, the scan path should cover as much of the area as possible while also taking into account the scan range and movement capabilities of the device. Some automated algorithms, such as genetic algorithms, simulated annealing, etc., may be employed to optimize the scan path. Converting the scan path into a path plan, i.e., determining the scan order and scan direction for each scan region, ensures that the device can scan each region completely and reduces overlap and absence of scans as much as possible.
Step 4: performing depth image data acquisition by using an RGBD camera according to the path scheme planned in the step 3, and obtaining a time sequence data packet; the time-series data packet includes a depth image, acceleration data, and a time stamp.
Setting the discrete data acquisition interval as deltat, acquiring depth image data at equal time intervals, and recording as D 1 ，D 2 ，...，D n Wherein D is n Represents a single frame depth image acquired using an RGBD camera at a time point of nth Δt, which is represented in the form of h×w×1, H and W representing the length and width of the depth image, respectively. Collecting acceleration data at equal intervals, denoted as a 1 ，a 2 ，..，a n Wherein a is n The acceleration vector acquired by using an inertial navigation module (IMU) built in the RGBD camera at the nth Δt time point is represented, and includes a value and a direction. Collecting the acquired depth image, acceleration data and time stamp into a time sequence data packet, wherein the data structure is [ (D) 1 ，a 1 )，(D 2 ，a 2 )，...，(D n ，a n )]Wherein (D) n ，a n ) Representing the acquisition using RGBD camera at the nth Δt time pointA depth image and an acceleration vector at the same time.
Step 5: and carrying out continuous frame point cloud conversion and adjacent frame matching on the obtained time sequence data packet according to an RTAB-MAP computer vision algorithm to obtain the ancient building scene model. For specific procedures reference is made to Labb. E M, michaud F.RTAB-Map as an open-source lidar and visual simultaneous localization and mapping library for large-scale and long-term online operation [ J ]. Journal of Field Robotics,2019,36 (2): 416-446.
Example 2
An RGBD-based lightweight historic building scene scanning and reconstruction system comprising an RGBD camera, a microprocessor and a memory, interconnected, the microprocessor programmed or configured to perform the steps of the lightweight historic building scene scanning and reconstruction method of embodiment 1.
Example 3
A computer readable storage medium having stored therein a computer program for programming or configuring by a microprocessor to perform the steps of the lightweight historic building scene scanning and reconstruction method of embodiment 1.
By adjusting the process parameters according to the present disclosure, the graphene/cellulose-based composite aerogel of the present disclosure can be prepared and exhibit substantially the same properties as example 1.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims (10)

1. The RGBD-based light-weight historic building scene scanning and reconstructing method is characterized by comprising the following steps of:
step 1: adjusting and fixing the height and angle of the RGBD camera according to the elevation height of the ancient building to be scanned and the maximum visual field range of the RGBD camera;
step 2: estimating the size of the ancient building to be collected, and dividing a scanning area by combining the surrounding environment;
step 3: determining a scanning path according to the shape and the size of each scanning area divided in the step 2, and converting the scanning path into a path scheme;
step 4: performing depth image data acquisition by using an RGBD camera according to the path scheme planned in the step 3, and obtaining a time sequence data packet;
step 5: and carrying out continuous frame point cloud conversion and adjacent frame matching on the obtained time sequence data packet to obtain the ancient building scene model.
2. The method for scanning and reconstructing a lightweight historic building scene according to claim 1, wherein the elevation of the historic building to be scanned comprises all parts from ground to roof.
3. The method for scanning and reconstructing a light-weight historic building scene according to claim 2, wherein the single scan height of the RGBD camera is greater than the elevation height of the historic building to be scanned at the height and angle of the RGBD camera fixed in step 1.
4. The method for scanning and reconstructing a light-weight historic building scene according to claim 2, wherein when the elevation height of the historic building to be scanned is greater than 8 meters, the complete elevation data is acquired by adopting a multi-scanning splicing mode.
5. The method for scanning and reconstructing a light-weight historic building scene according to claim 1, wherein in step 2, firstly, the dimensions of the historic building to be acquired are estimated, including the length, the width, the height and the geometric shapes of all parts, and references are provided for dividing the scanning area by combining the cruising ability of the scanning equipment;
then, surrounding roads, squares and buildings are also brought into the scanning range so as to ensure the integrity of the scanning result;
and finally, dividing the whole scanning range into a plurality of small areas according to the field condition and the parameters and the cruising ability of the scanning equipment so as to scan each area respectively.
6. The method for scanning and reconstructing a lightweight historic building scene according to claim 1, wherein in step 3, a genetic algorithm or simulated annealing is used to optimize the scanning path.
7. The lightweight historic building scene scanning and reconstruction method of claim 1, wherein the time series data packets comprise depth images, acceleration data and time stamps.
8. The method for scanning and reconstructing a lightweight historic building scene according to claim 1, wherein in step 5, continuous frame point cloud conversion and adjacent frame matching are performed on the obtained time series data packet according to a RTAB-MAP type computer vision algorithm.
9. An RGBD-based lightweight historic building scene scanning and reconstruction system comprising an RGBD camera, a microprocessor and a memory, interconnected, said microprocessor being programmed or configured to perform the steps of the lightweight historic building scene scanning and reconstruction method of any of claims 1-8.
10. A computer readable storage medium having stored therein a computer program for programming or configuring by a microprocessor to perform the steps of the lightweight historic building scene scanning and reconstruction method of any of claims 1-8.
CN202310959549.2A 2023-08-01 2023-08-01 RGBD-based light-weight ancient architecture scene scanning and reconstructing method Pending CN116934976A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310959549.2A CN116934976A (en) 2023-08-01 2023-08-01 RGBD-based light-weight ancient architecture scene scanning and reconstructing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310959549.2A CN116934976A (en) 2023-08-01 2023-08-01 RGBD-based light-weight ancient architecture scene scanning and reconstructing method

Publications (1)

Publication Number Publication Date
CN116934976A true CN116934976A (en) 2023-10-24

Family

ID=88387745

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310959549.2A Pending CN116934976A (en) 2023-08-01 2023-08-01 RGBD-based light-weight ancient architecture scene scanning and reconstructing method

Country Status (1)

Country Link
CN (1) CN116934976A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117665032A (en) * 2024-02-01 2024-03-08 国仪量子技术(合肥)股份有限公司 Scanning method, scanning device, scanning system, storage medium and electronic equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117665032A (en) * 2024-02-01 2024-03-08 国仪量子技术(合肥)股份有限公司 Scanning method, scanning device, scanning system, storage medium and electronic equipment
CN117665032B (en) * 2024-02-01 2024-05-14 国仪量子技术(合肥)股份有限公司 Scanning method, scanning device, scanning system, storage medium and electronic equipment

Similar Documents

Publication Publication Date Title
Zlot et al. Efficiently capturing large, complex cultural heritage sites with a handheld mobile 3D laser mapping system
US8818770B2 (en) Pitch determination systems and methods for aerial roof estimation
US20100114537A1 (en) Concurrent display systems and methods for aerial roof estimation
US11790542B2 (en) Mapping and localization system for autonomous vehicles
CN101545776B (en) Method for obtaining digital photo orientation elements based on digital map
CN112380312B (en) Laser map updating method based on grid detection, terminal and computer equipment
CN111207762B (en) Map generation method and device, computer equipment and storage medium
CN109871739B (en) Automatic target detection and space positioning method for mobile station based on YOLO-SIOCTL
CN116934976A (en) RGBD-based light-weight ancient architecture scene scanning and reconstructing method
CN111104850B (en) Remote sensing image building automatic extraction method and system based on residual error network
CN115690338A (en) Map construction method, map construction device, map construction equipment and storage medium
CN116129067A (en) Urban live-action three-dimensional modeling method based on multi-source geographic information coupling
CN116429116A (en) Robot positioning method and equipment
CN116883604A (en) Three-dimensional modeling technical method based on space, air and ground images
CN114372303B (en) Rapid construction method of light-weight BIM model of beam-bridge bottom structure
Dursun et al. 3D city modelling of Istanbul historic peninsula by combination of aerial images and terrestrial laser scanning data
CN115542338A (en) Laser radar data learning method based on point cloud space distribution mapping
Shan et al. Rapid full-field deformation measurements of tall buildings using UAV videos and deep learning
Zhang et al. An overlap-free calibration method for LiDAR-camera platforms based on environmental perception
Markovic et al. Application of modern technologies in assessing facade condition of building structures
Zhang et al. Research on 3D modeling of UAV tilt photogrammetry
Gu et al. Surveying and mapping of large-scale 3D digital topographic map based on oblique photography technology
CN115166686B (en) Multi-unmanned aerial vehicle distributed cooperative positioning and mapping method in satellite rejection environment
CN116222579B (en) Unmanned aerial vehicle inspection method and system based on building construction
Paal et al. Use Cases for Architects and Engineers

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