CN116844068B - Building mapping method, system, computer equipment and storage medium - Google Patents
Building mapping method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116844068B CN116844068B CN202311122604.9A CN202311122604A CN116844068B CN 116844068 B CN116844068 B CN 116844068B CN 202311122604 A CN202311122604 A CN 202311122604A CN 116844068 B CN116844068 B CN 116844068B
- Authority
- CN
- China
- Prior art keywords
- building
- data
- module
- point cloud
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000013507 mapping Methods 0.000 title claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 94
- 238000012545 processing Methods 0.000 claims abstract description 94
- 238000004458 analytical method Methods 0.000 claims abstract description 87
- 238000001914 filtration Methods 0.000 claims abstract description 48
- 238000005457 optimization Methods 0.000 claims abstract description 46
- 238000000605 extraction Methods 0.000 claims abstract description 40
- 238000005516 engineering process Methods 0.000 claims abstract description 35
- 238000007418 data mining Methods 0.000 claims abstract description 24
- 238000010801 machine learning Methods 0.000 claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims abstract description 19
- 230000009467 reduction Effects 0.000 claims abstract description 14
- 238000005265 energy consumption Methods 0.000 claims description 30
- 238000007781 pre-processing Methods 0.000 claims description 22
- 239000000463 material Substances 0.000 claims description 18
- 230000002146 bilateral effect Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000000491 multivariate analysis Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C15/00—Surveying instruments or accessories not provided for in groups G01C1/00 - G01C13/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/35—Constructional details or hardware or software details of the signal processing chain
- G01S19/37—Hardware or software details of the signal processing chain
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Radar, Positioning & Navigation (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Astronomy & Astrophysics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of building mapping methods, in particular to a building mapping method, a system, computer equipment and a storage medium, wherein the building mapping method comprises the following steps: combining unmanned plane, laser scanning and global navigation satellite system to obtain building original data. The method has the advantages that high-resolution images and accurate point cloud data of the building can be obtained by combining an unmanned plane, laser scanning and a global navigation satellite system, the acquired building original data are subjected to definition, noise reduction, enhancement, filtering and sparse processing, the quality of the data is ensured, the optimized data are subjected to feature extraction and classification by using deep learning and machine learning algorithms, the accuracy and efficiency of feature extraction are improved, the three-dimensional model of the building is rebuilt by using radar technology and point cloud processing algorithms, a high-precision building model is provided, the multi-objective analysis is performed on the building by using data mining and multi-element analysis algorithms, and a comprehensive building optimization scheme is generated.
Description
Technical Field
The invention relates to the technical field of building mapping methods, in particular to a building mapping method, a system, computer equipment and a storage medium.
Background
Building mapping methods are used for measuring and drawing buildings through specific technologies and tools to acquire accurate data and image information of the buildings. The main purpose of the method is to collect the spatial and geographical information of the building, including the size, shape, position and the like of the building, and record and analyze the characteristics of the building. Through the building mapping method, the effects of building planning and design, construction and engineering management, building change and repair and the like can be realized. The purposes of surveying and mapping are generally achieved by means of ground measuring instruments, remote sensing, unmanned aerial vehicles, laser scanning, indoor laser scanning and the like, so that accurate and detailed building data are provided, and support and guidance are provided for links such as building design, construction and management.
In building mapping methods, existing methods typically rely on a single data source only, often on satellite images or ground-captured pictures only, which results in data incompleteness and inaccuracy. The existing method is often not fine enough in data processing, and computer vision and image processing technology cannot be fully utilized to preprocess the data. Existing methods typically do not employ machine learning and deep learning algorithms, resulting in poor accuracy and efficiency of feature extraction. The existing method generally fails to fully utilize radar technology and point cloud processing algorithms, so that the reconstructed three-dimensional model is not accurate enough. Existing methods typically analyze only a single aspect of the building, such as only structural stability, and ignore other important aspects of energy consumption, efficiency of use, etc., resulting in a single-sided comparison of the end results.
Disclosure of Invention
The object of the present invention is to solve the drawbacks of the prior art and to propose a method, a system, a computer device and a storage medium for building mapping.
In order to achieve the above purpose, the present invention adopts the following technical scheme: a method of building mapping comprising the steps of:
s1: combining an unmanned plane, laser scanning and a global navigation satellite system, and acquiring high-resolution images and accurate point cloud data of a target building to obtain building original data;
s2: preprocessing the building original data, performing the operations of sharpening, noise reduction and enhancement on the image by utilizing image processing and a computer vision algorithm, and simultaneously performing the filtering and sparse processing of the point cloud data to obtain optimized building data;
s3: performing feature extraction and classification on the optimized building data by using a deep learning and machine learning algorithm, and identifying the structure, materials and purposes of a building to generate building feature classification information;
s4: according to the building characteristic classification information, a radar technology and a point cloud processing algorithm are combined to reconstruct a three-dimensional model of a building, and the three-dimensional model of the building is built;
s5: and according to the three-dimensional model of the building, performing multi-objective analysis comprising structure, energy consumption and use efficiency on the building by utilizing a data mining and multivariate analysis algorithm to generate a building optimization scheme.
As a further scheme of the invention, combining an unmanned plane, laser scanning and a global navigation satellite system, the method for acquiring the high-resolution image and accurate point cloud data of the target building comprises the following steps of:
s101: the unmanned aerial vehicle is matched with a computer vision algorithm to acquire high-resolution images, and algorithms such as feature extraction and matching are adopted to capture panorama and details of a building, so that a high-definition flight image set is acquired;
s102: acquiring three-dimensional information of a building by using a laser scanner, and performing preliminary processing and outlier filtering on the data by using an octree downsampling method and a random sampling consistency algorithm to obtain point cloud data after the preliminary processing and filtering;
s103: using a high-precision global navigation satellite system receiver to record the geographic coordinates of a building, and performing position optimization through Kalman filtering to obtain optimized geographic coordinate data;
s104: and integrating the high-definition flight image set, the point cloud data after preliminary processing and filtering and the optimized geographic coordinate data by using a differential geometric mean color recovery algorithm to form building comprehensive original data.
As a further scheme of the invention, the building original data is preprocessed, the image is subjected to the operations of sharpening, noise reduction and enhancement by utilizing the image processing and a computer vision algorithm, and meanwhile, the filtering and the sparse processing of the point cloud data are carried out, and the optimized building data are obtained by the steps of:
S201: applying an image processing algorithm to the high-definition flying image set, and obtaining a clear enhanced image by adopting histogram equalization and bilateral filtering;
s202: performing voxel grid filtering and rapid bilateral filtering on the point cloud data subjected to preliminary processing and filtering, optimizing a point cloud data structure, and further optimizing in a point sampling mode in each plane to obtain optimized point cloud data;
s203: and performing geometric correction and fusion on the optimized point cloud data and the clear enhanced image by using a point cloud registration algorithm to obtain optimized building data.
As a further scheme of the invention, the method utilizes deep learning and machine learning algorithms to extract and classify the characteristics of the optimized building data, and identifies the structure, the materials and the purposes of the building, and the steps of generating the building characteristic classification information are specifically as follows:
s301: performing depth feature extraction on the optimized building data by using a convolutional neural network, extracting local features by using a scale-invariant feature transformation algorithm, and generating depth feature data;
s302: evaluating a support vector machine and a decision tree algorithm by using a confusion matrix, and selecting a model with the best performance to classify the depth feature data to obtain building feature classification information;
S303: based on the building characteristic classification information, combining system characteristics and construction information, adopting a knowledge graph method to identify the structure, materials and purposes of the building, and providing a building identification report.
As a further scheme of the invention, according to the building feature classification information and in combination with radar technology and point cloud processing algorithm, reconstructing a three-dimensional model of a building, and establishing the three-dimensional model of the building specifically comprises the following steps:
s401: performing registration processing on the optimized point cloud data by combining a deep learning technology and a point cloud registration algorithm, wherein the registration processing comprises global registration and detail processing, and acquiring registered point cloud data;
s402: based on the registered point cloud data, rapidly dividing and classifying unordered point cloud data by using a global feature descriptor based on a shape histogram, and obtaining the divided and classified point cloud data;
s403: and three-dimensional modeling is carried out on the segmented and classified point cloud data by using a Poisson surface reconstruction algorithm and a grid processing tool, so as to generate a three-dimensional building model.
As a further scheme of the present invention, according to the three-dimensional model of the building, the multi-objective analysis including structure, energy consumption and use efficiency is performed on the building by using data mining and a multi-element analysis algorithm, and the steps for generating the building optimization scheme specifically include:
S501: based on the building three-dimensional model, analyzing the structure and energy consumption of the building by using a building information model tool, and simultaneously examining the environmental influence of the building to obtain a building performance report;
s502: based on the building performance report and the building feature classification information, adopting a data mining technology to deeply analyze building performance data to generate a building performance analysis result, wherein the building performance analysis result comprises building use efficiency, energy consumption and space utilization;
s503: combining the building feature classification information and the data mining technology, identifying potential problem identification results, and marking and classifying potential problems existing in the building;
s504: and comprehensively analyzing the use efficiency and the potential problems of the building based on the building performance analysis result and the potential problem identification result in combination with the building identification report to generate a building optimization scheme.
The building mapping system is used for executing the building mapping method and consists of a data acquisition module, a data preprocessing module, a feature extraction and classification module, a three-dimensional reconstruction module, a multi-target analysis module and a comprehensive report module;
the data acquisition module is combined with an unmanned aerial vehicle, laser scanning and a global navigation satellite system, and high-resolution images and accurate point cloud data of a target building are acquired through unmanned aerial vehicle image acquisition, laser scanning and global navigation satellite system positioning technologies, so that building original data are established;
The data preprocessing module performs image processing and point cloud processing on the building original data, and comprises the steps of performing sharpening, noise reduction and enhancement on the image, performing filtering and sparse processing on the point cloud data, and obtaining optimized building data;
the feature extraction and classification module extracts building features from the optimized building data by using a deep learning and machine learning algorithm, classifies the building features, identifies the structure, the material and the purpose of the building, and identifies the building by using a knowledge graph method to generate building feature classification information;
the three-dimensional reconstruction module performs three-dimensional reconstruction on a building by utilizing a radar technology, a point cloud registration algorithm and a surface reconstruction algorithm, wherein the three-dimensional reconstruction comprises registration processing, segmentation and classification of point cloud data and surface reconstruction, and a three-dimensional building model is generated;
the multi-objective analysis module is used for carrying out multi-objective analysis on the structure, the energy consumption and the use efficiency of the building by utilizing a data mining and multi-element analysis algorithm based on a three-dimensional model of the building to generate a building optimization scheme;
the comprehensive report module is used for comprehensively analyzing the use efficiency and the potential problems of the building by combining the building characteristic classification information, the building performance analysis result and the potential problem identification result, and giving a building optimization suggestion report.
As a further scheme of the invention, the data acquisition module comprises an unmanned aerial vehicle image acquisition sub-module, a laser scanning sub-module and a global navigation satellite system positioning sub-module;
the data preprocessing module comprises an image processing sub-module and a point cloud processing sub-module;
the feature extraction and classification module comprises a deep feature extraction sub-module, a machine learning classification sub-module and a building identification sub-module;
the three-dimensional reconstruction module comprises a point cloud registration sub-module, a segmentation and classification sub-module and a surface reconstruction sub-module;
the multi-target analysis module comprises a structure analysis sub-module, an energy consumption analysis sub-module and a use efficiency analysis sub-module;
the comprehensive report module comprises a building performance analysis sub-module, a potential problem identification sub-module and a building optimization suggestion sub-module.
Computer device comprising a memory and a processor, the memory having stored therein a computer program, which when executed by the processor implements the steps of the building mapping method as described above.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a building mapping method as described above.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, by combining an unmanned plane, laser scanning and a global navigation satellite system, high-resolution images of a building and accurate point cloud data can be obtained, so that the comprehensiveness and accuracy of data acquisition are ensured. The acquired building original data are subjected to the processes of definition, noise reduction, enhancement, filtering and sparseness, so that the quality of the data is ensured, and a good foundation is laid for the subsequent steps. And the optimized data is subjected to feature extraction and classification by using deep learning and machine learning algorithms, so that the accuracy and the efficiency of feature extraction are greatly improved. And the three-dimensional model of the building is rebuilt by using radar technology and a point cloud processing algorithm, so that a high-precision building model is provided. And performing multi-objective analysis on the building by utilizing data mining and a multi-element analysis algorithm, wherein the multi-objective analysis comprises multiple aspects of structure, energy consumption, use efficiency and the like, so that a comprehensive building optimization scheme is generated.
Drawings
FIG. 1 is a schematic workflow diagram of the present invention;
FIG. 2 is a S1 refinement flowchart of the present invention;
FIG. 3 is a S2 refinement flowchart of the present invention;
FIG. 4 is a S3 refinement flowchart of the present invention;
FIG. 5 is a S4 refinement flowchart of the present invention;
FIG. 6 is a S5 refinement flowchart of the present invention;
FIG. 7 is a system flow diagram of the present invention;
fig. 8 is a system block diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. 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.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
Referring to fig. 1, the present invention provides a technical solution: a method of building mapping comprising the steps of:
s1: combining an unmanned plane, laser scanning and a global navigation satellite system, and acquiring high-resolution images and accurate point cloud data of a target building to obtain building original data;
s2: preprocessing building original data, performing the operations of sharpening, noise reduction and enhancement on the image by utilizing image processing and a computer vision algorithm, and simultaneously performing the filtering and sparse processing of point cloud data to obtain optimized building data;
s3: performing feature extraction and classification on the optimized building data by using a deep learning and machine learning algorithm, and identifying the structure, materials and purposes of a building to generate building feature classification information;
s4: according to the building characteristic classification information, a radar technology and a point cloud processing algorithm are combined to reconstruct a three-dimensional model of a building, and the three-dimensional model of the building is built;
s5: and according to the three-dimensional model of the building, performing multi-objective analysis including structure, energy consumption and use efficiency on the building by utilizing a data mining and multivariate analysis algorithm to generate a building optimization scheme.
The building mapping method comprehensively utilizes advanced technologies such as unmanned aerial vehicle, laser scanning and global navigation satellite system, and methods such as image processing, computer vision, deep learning and machine learning algorithms, and the like, so that comprehensive mapping and analysis of a building are realized. The building original data is obtained through the collection of the high-resolution image and the accurate point cloud data, and the high-quality building data is obtained through preprocessing optimization including image definition, noise reduction, enhancement, point cloud filtering and sparse processing. Further, the optimized building data is subjected to feature extraction and classification by utilizing deep learning and machine learning algorithms, and information such as structure, material, application and the like of a building can be identified, so that building feature classification information is generated. And according to the building characteristic classification information, combining a radar technology and a point cloud processing algorithm, carrying out three-dimensional reconstruction on the building, and establishing a three-dimensional model of the building. And finally, performing multi-objective analysis by applying a data mining and multivariate analysis algorithm based on a three-dimensional model of the building, wherein the multi-objective analysis comprises comprehensive evaluation on the aspects of structure, energy consumption, use efficiency and the like of the building, and generating a building optimization scheme. The method can provide comprehensive building information and optimization suggestions, and is beneficial to application in the fields of building design, management, decision making and the like.
Referring to fig. 2, in combination with an unmanned plane, laser scanning and a global navigation satellite system, the steps of acquiring high-resolution images and accurate point cloud data of a target building to obtain building original data are specifically as follows:
s101: the unmanned aerial vehicle is matched with a computer vision algorithm to acquire high-resolution images, and algorithms such as feature extraction and matching are adopted to capture panorama and details of a building, so that a high-definition flight image set is acquired;
s102: acquiring three-dimensional information of a building by using a laser scanner, and performing preliminary processing and outlier filtering on the data by using an octree downsampling method and a random sampling consistency algorithm to obtain point cloud data after the preliminary processing and filtering;
s103: using a high-precision global navigation satellite system receiver to record the geographic coordinates of a building, and performing position optimization through Kalman filtering to obtain optimized geographic coordinate data;
s104: and integrating the high-definition flight image set, the point cloud data after preliminary processing and filtering and the optimized geographic coordinate data by using a differential geometric mean color recovery algorithm to form building comprehensive original data.
Firstly, the unmanned aerial vehicle can realize high-resolution building image acquisition by using the unmanned aerial vehicle, capture the panorama and the details of a building, and provide rich viewing angles and information for subsequent analysis. And secondly, the laser scanner can acquire accurate three-dimensional information of the building, and high-quality point cloud data is obtained through preliminary processing and outlier filtering, so that accurate spatial expression is provided for the complex structure and the form of the building. Meanwhile, the application of the global navigation satellite system can record the geographic coordinates of the building, and the precision and accuracy of the coordinate data are further improved through a position optimization algorithm. And finally, integrating the high-definition flight image set, the point cloud data after preliminary processing and filtering and the optimized geographic coordinate data to form building comprehensive original data, thereby providing a foundation for subsequent building feature extraction, three-dimensional modeling and multi-target analysis.
The building mapping method has the following beneficial effects: the high-resolution building image and the accurate point cloud data are provided, so that details and structures of a building can be accurately captured and analyzed, and important references are provided for building design and management;
through the feature extraction and classification algorithm, the information such as the structure, the material, the use and the like of the building can be identified and classified, and a basis is provided for functional evaluation and improvement of the building;
the three-dimensional model is reconstructed and optimized, so that visual display and space analysis of the building can be performed, and convenience is provided for building design and planning decision-making;
the application of the data mining and multivariate analysis algorithm can comprehensively evaluate the structure, the energy consumption, the use efficiency and the like of the building, and provide guidance for optimizing a building scheme and improving the building performance.
Referring to fig. 3, preprocessing building original data, performing operations of sharpening, noise reduction and enhancement on an image by using image processing and a computer vision algorithm, and simultaneously performing filtering and sparse processing on point cloud data, wherein the steps of obtaining optimized building data specifically include:
s201: applying an image processing algorithm to the high-definition flying image set, and obtaining a clear enhanced image by adopting histogram equalization and bilateral filtering;
S202: performing voxel grid filtering and rapid bilateral filtering on the point cloud data subjected to preliminary processing and filtering, optimizing a point cloud data structure, and further optimizing in a point sampling mode in each plane to obtain optimized point cloud data;
s203: and performing geometric correction and fusion on the optimized point cloud data and the clear enhanced image by using a point cloud registration algorithm to acquire the optimized building data.
And preprocessing the building original data, including image processing and point cloud data processing, so as to obtain optimized building data. By applying image processing algorithms, such as histogram equalization and bilateral filtering, image sharpness may be enhanced, noise reduced, and more accurate details extracted. Meanwhile, the point cloud data is filtered and sparsely processed by utilizing the technologies of voxel grid filtering, rapid bilateral filtering, plane surface cutting interior point sampling and the like, so that the data structure is optimized, and noise and redundancy are reduced. And finally, fusing the optimized point cloud data with the clearly enhanced image through a point cloud registration algorithm and geometric correction to obtain building data with high consistency and high accuracy. The preprocessing method can improve the quality of building images, reduce data noise, optimize data structures, provide accurate point cloud information and clear image details, and provide more accurate and reliable data bases for building analysis, design, evaluation and other applications.
Referring to fig. 4, the method for extracting and classifying features of the optimized building data by using deep learning and machine learning algorithms, and identifying the structure, material and purpose of the building specifically includes the steps of:
s301: performing depth feature extraction on the optimized building data by using a convolutional neural network, and extracting local features by using a scale-invariant feature transformation algorithm to generate depth feature data;
s302: evaluating a support vector machine and a decision tree algorithm by using a confusion matrix, and selecting a model with the best performance to classify depth feature data to obtain building feature classification information;
s303: based on the building characteristic classification information, combining the system characteristics and the construction information, adopting a knowledge graph method to identify the structure, the material and the application of the building, and providing a building identification report.
Firstly, the automatic feature extraction and classification greatly improves the processing efficiency, reduces the workload of manual operation, and ensures the consistency and accuracy of classification results. And secondly, through multi-attribute building identification, the characteristics of the building can be more comprehensively known and analyzed, and valuable information is provided for the fields of building design, planning, evaluation and the like. In addition, the application of the knowledge graph method can combine the building characteristic classification information with the existing building knowledge, further analyze the structure, the materials and the application of the building, and provide more comprehensive and accurate description and understanding of the attributes and the characteristics of the building.
Referring to fig. 5, according to the building feature classification information, in combination with radar technology and point cloud processing algorithm, the three-dimensional model of the building is reconstructed, and the building three-dimensional model is built specifically by the steps of:
s401: performing registration processing on the optimized point cloud data by combining a deep learning technology and a point cloud registration algorithm, wherein the registration processing comprises global registration and detail processing, and acquiring registered point cloud data;
s402: based on the registered point cloud data, rapidly dividing and classifying unordered point cloud data by using a global feature descriptor based on a shape histogram, and obtaining the divided and classified point cloud data;
s403: and three-dimensional modeling is carried out on the segmented and classified point cloud data by using a Poisson surface reconstruction algorithm and a grid processing tool, so as to generate a three-dimensional model of the building.
Firstly, through registering the optimized point cloud data, the accuracy and consistency of the three-dimensional model can be improved, and the reconstructed model is more accurate. And secondly, carrying out rapid segmentation and classification on point cloud data by using the shape descriptor, and generating a building model with semantic information to realize identification of different parts and elements. Such semantically aware building models are of great significance in building design and visualization. Finally, the quality of the three-dimensional model can be further improved, noise is removed, and the surface is smoothed by applying a poisson surface reconstruction algorithm and an optimization tool.
Referring to fig. 6, according to a three-dimensional model of a building, using data mining and multivariate analysis algorithms, a multi-objective analysis including structure, energy consumption and use efficiency is performed on the building, and the steps for generating a building optimization scheme are specifically as follows:
s501: based on a three-dimensional model of a building, analyzing the structure and energy consumption of the building by using a building information model tool, and simultaneously examining the environmental influence of the building to obtain a building performance report;
s502: based on the building performance report and the building feature classification information, adopting a data mining technology to deeply analyze the performance data of the building to generate a building performance analysis result, wherein the building performance analysis result comprises building use efficiency, energy consumption and space utilization;
s503: combining building feature classification information and a data mining technology, identifying potential problem identification results, and marking and classifying potential problems existing in the building;
s504: and comprehensively analyzing the use efficiency and the potential problems of the building based on the building performance analysis result and the potential problem identification result in combination with the building identification report to generate a building optimization scheme.
First, by deeply analyzing building performance data, including structural, energy consumption, and use efficiency, the performance of a building can be comprehensively understood, and potential problems and room for improvement are found. This provides the basis for formulating a targeted optimization scheme. Secondly, the application of the data mining technology can reveal hidden modes and associations, so that the relation between building performance and each factor is better understood, and a scientific basis is provided for subsequent decisions. In addition, through comprehensive building performance analysis results and potential problem identification, a specific building optimization scheme can be formulated, and the method relates to structural optimization, energy conservation, space utilization improvement and the like. The optimization schemes can improve the overall performance and sustainability of the building and bring about the improvement of resource efficiency. Most importantly, application of data mining and multivariate analysis techniques can enable objective decision support, helping a decision maker to make accurate decisions based on data and evidence when optimizing a building.
Referring to fig. 7, the building mapping system is used for executing the building mapping method, and is composed of a data acquisition module, a data preprocessing module, a feature extraction and classification module, a three-dimensional reconstruction module, a multi-objective analysis module and a comprehensive report module;
the data acquisition module is combined with the unmanned aerial vehicle, the laser scanning and the global navigation satellite system, and high-resolution images and accurate point cloud data of a target building are acquired through unmanned aerial vehicle image acquisition, laser scanning and global navigation satellite system positioning technologies, so that building original data are established;
the data preprocessing module performs image processing and point cloud processing on the building original data, and comprises the steps of performing sharpening, noise reduction and enhancement on the image, optimizing the point cloud data through filtering and sparse processing, and obtaining optimized building data;
the feature extraction and classification module extracts building features from the optimized building data by using a deep learning and machine learning algorithm, classifies the building features, identifies the structure, the material and the purpose of the building, and uses a knowledge graph method to identify the building so as to generate building feature classification information;
the three-dimensional reconstruction module performs three-dimensional reconstruction on the building by utilizing a radar technology, a point cloud registration algorithm and a surface reconstruction algorithm, wherein the three-dimensional reconstruction comprises registration processing, segmentation and classification of point cloud data and surface reconstruction, and a three-dimensional model of the building is generated;
The multi-objective analysis module is used for carrying out multi-objective analysis on the structure, the energy consumption and the use efficiency of the building by utilizing a data mining and multi-element analysis algorithm based on the three-dimensional model of the building to generate a building optimization scheme;
the comprehensive report module is used for comprehensively analyzing the use efficiency and the potential problems of the building by combining the building characteristic classification information, the building performance analysis result and the potential problem identification result, and giving a building optimization suggestion report.
Firstly, the data acquisition module can acquire high-resolution images and accurate point cloud data by combining technologies such as unmanned aerial vehicle, laser scanning, global navigation satellite system and the like, and original data of a building is established. The accuracy and richness of these data provides a reliable basis for subsequent processing and analysis.
And secondly, the data preprocessing module performs operations such as sharpening, noise reduction, enhancement and the like on the original data through image processing and point cloud processing, and optimizes the data quality. The preprocessing steps can improve the accuracy and usability of data and provide clear and reliable input for the work of the subsequent modules.
The feature extraction and classification module extracts features from the optimized building data by using a deep learning and machine learning algorithm and classifies the features to identify the structure, the material and the purpose of the building. The process of feature extraction and classification is helpful for building feature classification information, and provides a basis for subsequent analysis and optimization.
The three-dimensional reconstruction module performs three-dimensional reconstruction on the building by using a radar technology, a point cloud registration algorithm and a surface reconstruction algorithm to generate a three-dimensional model of the building. These steps can provide an accurate representation of the shape and structure of the building, providing basic data for building analysis and optimization.
The multi-target analysis module is used for analyzing a plurality of targets by utilizing a data mining and multivariate analysis algorithm based on a three-dimensional model of the building, and the analysis comprises the aspects of structure, energy consumption, use efficiency and the like of the building. Such analysis may reveal problems and improvement potential of building performance and generate corresponding optimization schemes and decision support.
The comprehensive report module is used for comprehensively analyzing the use efficiency of the building and the potential problems by combining the building characteristic classification information, the building performance analysis result and the potential problem identification result, and generating a comprehensive report. Such comprehensive reports may provide a decision maker with comprehensive building optimization suggestions and directions of improvement.
Referring to fig. 8, the data acquisition module includes an unmanned aerial vehicle image acquisition sub-module, a laser scanning sub-module, and a global navigation satellite system positioning sub-module;
the data preprocessing module comprises an image processing sub-module and a point cloud processing sub-module;
The feature extraction and classification module comprises a deep feature extraction sub-module, a machine learning classification sub-module and a building identification sub-module;
the three-dimensional reconstruction module comprises a point cloud registration sub-module, a segmentation and classification sub-module and a surface reconstruction sub-module;
the multi-target analysis module comprises a structure analysis sub-module, an energy consumption analysis sub-module and a use efficiency analysis sub-module;
the comprehensive report module comprises a building performance analysis sub-module, a potential problem identification sub-module and a building optimization suggestion sub-module.
Firstly, unmanned aerial vehicle image acquisition submodule, laser scanning submodule and global navigation satellite system positioning submodule of data acquisition module can work cooperatively, realize the acquisition of high-resolution image and accurate point cloud data. This provides an accurate data basis for detailed modeling of the building, improving the visualization and quantification capabilities of the building features.
And secondly, an image processing sub-module and a point cloud processing sub-module of the data preprocessing module can perform the processing of sharpening, noise reduction, enhancement and the like on the acquired data. Such preprocessing can improve the quality and accuracy of the data, providing a more reliable basis for subsequent feature extraction and analysis.
The depth feature extraction sub-module, the machine learning classification sub-module and the building identification sub-module of the feature extraction and classification module can extract feature information of a building from optimized data and accurately classify and identify the feature information. Such feature extraction and classification can provide detailed building feature classification information for subsequent building analysis and optimization, helping building owners, designers, and decision makers to better understand the structure, materials, and uses of the building.
The point cloud registration sub-module, the segmentation and classification sub-module and the surface reconstruction sub-module of the three-dimensional reconstruction module can accurately reconstruct the three-dimensional of the building. By registration, segmentation and reconstruction, a three-dimensional model of the building with high accuracy and integrity can be generated. Such a three-dimensional model provides the basis for subsequent multi-objective analysis and formulation of an optimization scheme.
The structure analysis submodule, the energy consumption analysis submodule and the use efficiency analysis submodule of the multi-target analysis module can analyze multiple aspects of a building, including aspects of structure, energy consumption, use efficiency and the like. Such multi-objective analysis can reveal problems and potential for building performance and provide relevant data support for the formulation of optimization schemes.
The building performance analysis sub-module, the potential problem identification sub-module and the building optimization suggestion sub-module of the comprehensive report module can comprehensively consider the performance analysis result and the potential problem identification result of the building and formulate comprehensive building optimization suggestions. Such integrated reports may provide comprehensive building performance assessment and improvement recommendations, providing feasibility and operability recommendations for the decision maker.
Computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of the building mapping method as described above.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a building mapping method as described above.
Working principle:
firstly, an unmanned aerial vehicle image acquisition sub-module is utilized to acquire high-resolution images through carried image pickup equipment, and panorama and details of a building are captured by using a feature extraction and matching algorithm to acquire a high-definition flight image set. Meanwhile, the laser scanning sub-module acquires three-dimensional information of a building by using a laser scanner, and the point cloud data after preliminary processing and filtering are obtained through preliminary processing and outlier filtering. The global navigation satellite system positioning sub-module records the geographic coordinates of the building, performs position optimization through Kalman filtering, and acquires optimized geographic coordinate data. And the comprehensive module integrates the high-definition flight image set, the point cloud data and the geographic coordinate data into building comprehensive original data.
The data preprocessing module follows. The image processing sub-module applies image processing algorithms, such as histogram equalization and bilateral filtering, to the high definition fly-image set to obtain a sharpness-enhanced image. The point cloud processing sub-module performs filtering and sparse processing on the point cloud data, such as voxel grid filtering, rapid bilateral filtering and planar cut interior point sampling, so as to optimize the point cloud data structure.
Then the feature extraction and classification module. The depth feature extraction submodule extracts depth features of building data by using a convolutional neural network, and extracts local features by adopting a scale-invariant feature transformation algorithm to generate depth feature data. The machine learning classifying sub-module evaluates and classifies the depth characteristic data, uses algorithms such as a support vector machine, a decision tree and the like, and acquires building characteristic classifying information. The building identification submodule is used for identifying the structure, the material and the application of the building by adopting a knowledge graph method and generating a building identification report by combining building characteristic classification information, system characteristics and construction information.
The three-dimensional reconstruction module follows. The point cloud registration sub-module performs registration processing on the optimized point cloud data by using a deep learning technology and a point cloud registration algorithm, wherein the registration processing comprises global registration and detail processing, and acquires the registered point cloud data. The segmentation and classification sub-module uses the global feature descriptor based on the shape histogram to quickly segment and classify the registered unordered point cloud data to obtain the segmented and classified point cloud data. The surface reconstruction sub-module utilizes a poisson surface reconstruction algorithm and a grid processing tool to carry out three-dimensional modeling on the segmented and classified point cloud data, and a three-dimensional model of the building is generated.
The multi-target analysis module comprises a structure analysis sub-module, and utilizes a building information model tool to carry out structure analysis on a building, including analysis on structural strength, stability and the like. The energy consumption analysis submodule utilizes the building information model tool to carry out energy consumption analysis on the building, and the energy consumption analysis comprises the energy consumption condition of the building and the energy utilization efficiency of the building optimization. The utilization efficiency analysis submodule adopts a data mining technology to carry out deep analysis on the utilization efficiency of the building based on a three-dimensional model and a performance report of the building, and comprises evaluation on space utilization, working efficiency and the like.
And finally, a comprehensive report module. And the building performance analysis submodule combines the building performance report and the building characteristic classification information to comprehensively analyze the performance data of the building. The potential problem identification sub-module is used for identifying potential problems existing in the building by combining building feature classification information and data mining technology, and marking and classifying the potential problems. The building optimization suggestion sub-module comprehensively analyzes the use efficiency and the potential problems of the building according to the building performance analysis result, the potential problem identification result and the building identification report, generates an optimization scheme of the building, and provides a corresponding optimization suggestion report.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (5)
1. A method of building mapping, comprising the steps of:
combining an unmanned plane, laser scanning and a global navigation satellite system, and acquiring high-resolution images and accurate point cloud data of a target building to obtain building original data;
preprocessing the building original data, performing the operations of sharpening, noise reduction and enhancement on the image by utilizing image processing and a computer vision algorithm, and simultaneously performing the filtering and sparse processing of the point cloud data to obtain optimized building data;
performing feature extraction and classification on the optimized building data by using a deep learning and machine learning algorithm, and identifying the structure, materials and purposes of a building to generate building feature classification information;
According to the building characteristic classification information, a radar technology and a point cloud processing algorithm are combined to reconstruct a three-dimensional model of a building, and the three-dimensional model of the building is built;
according to the three-dimensional model of the building, performing multi-objective analysis comprising structure, energy consumption and use efficiency on the building by utilizing a data mining and multivariate analysis algorithm to generate a building optimization scheme;
according to the building characteristic classification information, the three-dimensional model of the building is rebuilt by combining a radar technology and a point cloud processing algorithm, and the building three-dimensional model building method specifically comprises the following steps:
performing registration processing on the optimized point cloud data by combining a deep learning technology and a point cloud registration algorithm, wherein the registration processing comprises global registration and detail processing, and acquiring registered point cloud data;
based on the registered point cloud data, rapidly dividing and classifying unordered point cloud data by using a global feature descriptor based on a shape histogram, and obtaining the divided and classified point cloud data;
three-dimensional modeling is carried out on the segmented and classified point cloud data by using a Poisson surface reconstruction algorithm and a grid processing tool, and a three-dimensional building model is generated;
according to the three-dimensional model of the building, the multi-objective analysis comprising structure, energy consumption and use efficiency is carried out on the building by utilizing a data mining and multivariate analysis algorithm, and the steps for generating the building optimization scheme are as follows:
Based on the building three-dimensional model, analyzing the structure and energy consumption of the building by using a building information model tool, and simultaneously examining the environmental influence of the building to obtain a building performance report;
based on the building performance report and the building feature classification information, adopting a data mining technology to deeply analyze building performance data to generate a building performance analysis result, wherein the building performance analysis result comprises building use efficiency, energy consumption and space utilization;
combining the building feature classification information and the data mining technology, identifying potential problem identification results, and marking and classifying potential problems existing in the building;
based on the building performance analysis result and the potential problem identification result in combination with a building identification report, comprehensively analyzing the use efficiency and the potential problems of the building to generate a building optimization scheme;
combining an unmanned plane, laser scanning and a global navigation satellite system, and acquiring high-resolution images and accurate point cloud data of a target building, wherein the steps for obtaining building original data specifically comprise:
the unmanned aerial vehicle is matched with a computer vision algorithm to acquire high-resolution images, and a feature extraction and matching algorithm is adopted to capture panorama and details of a building, so as to acquire a high-definition flight image set;
Acquiring three-dimensional information of a building by using a laser scanner, and performing preliminary processing and outlier filtering on the data by using an octree downsampling method and a random sampling consistency algorithm to obtain point cloud data after the preliminary processing and filtering;
using a high-precision global navigation satellite system receiver to record the geographic coordinates of a building, and performing position optimization through Kalman filtering to obtain optimized geographic coordinate data;
integrating the high-definition flight image set, the point cloud data after preliminary processing and filtering and the optimized geographic coordinate data by using a differential geometric mean color recovery algorithm to form building comprehensive original data;
preprocessing the building original data, performing the operations of sharpening, noise reduction and enhancement on the image by utilizing an image processing and computer vision algorithm, and simultaneously performing the filtering and sparse processing of the point cloud data, wherein the steps of obtaining the optimized building data are specifically as follows:
applying an image processing algorithm to the high-definition flying image set, and obtaining a clear enhanced image by adopting histogram equalization and bilateral filtering;
performing voxel grid filtering and rapid bilateral filtering on the point cloud data subjected to preliminary processing and filtering, optimizing a point cloud data structure, and further optimizing in a point sampling mode in each plane to obtain optimized point cloud data;
Performing geometric correction and fusion on the optimized point cloud data and the clear enhanced image by using a point cloud registration algorithm to obtain optimized building data;
the method comprises the following steps of performing feature extraction and classification on optimized building data by utilizing a deep learning algorithm and a machine learning algorithm, and identifying the structure, the material and the application of a building, wherein the step of generating building feature classification information comprises the following specific steps:
performing depth feature extraction on the optimized building data by using a convolutional neural network, extracting local features by using a scale-invariant feature transformation algorithm, and generating depth feature data;
evaluating a support vector machine and a decision tree algorithm by using a confusion matrix, and selecting a model with the best performance to classify the depth feature data to obtain building feature classification information;
based on the building characteristic classification information, combining system characteristics and construction information, adopting a knowledge graph method to identify the structure, materials and purposes of the building, and providing a building identification report.
2. The building mapping system is used for executing the building mapping method of claim 1, and comprises a data acquisition module, a data preprocessing module, a feature extraction and classification module, a three-dimensional reconstruction module, a multi-target analysis module and a comprehensive report module;
The data acquisition module is combined with an unmanned aerial vehicle, laser scanning and a global navigation satellite system, and high-resolution images and accurate point cloud data of a target building are acquired through unmanned aerial vehicle image acquisition, laser scanning and global navigation satellite system positioning technologies, so that building original data are established;
the data preprocessing module performs image processing and point cloud processing on the building original data, and comprises the steps of performing sharpening, noise reduction and enhancement on the image, performing filtering and sparse processing on the point cloud data, and obtaining optimized building data;
the feature extraction and classification module extracts building features from the optimized building data by using a deep learning and machine learning algorithm, classifies the building features, identifies the structure, the material and the purpose of the building, and identifies the building by using a knowledge graph method to generate building feature classification information;
the three-dimensional reconstruction module performs three-dimensional reconstruction on a building by utilizing a radar technology, a point cloud registration algorithm and a surface reconstruction algorithm, wherein the three-dimensional reconstruction comprises registration processing, segmentation and classification of point cloud data and surface reconstruction, and a three-dimensional building model is generated;
the multi-objective analysis module is used for carrying out multi-objective analysis on the structure, the energy consumption and the use efficiency of the building by utilizing a data mining and multi-element analysis algorithm based on a three-dimensional model of the building to generate a building optimization scheme;
The comprehensive report module is used for comprehensively analyzing the use efficiency and the potential problems of the building by combining the building characteristic classification information, the building performance analysis result and the potential problem identification result, and giving a building optimization suggestion report.
3. The building mapping system of claim 2, wherein the data acquisition module comprises an unmanned aerial vehicle image acquisition sub-module, a laser scanning sub-module, a global navigation satellite system positioning sub-module;
the data preprocessing module comprises an image processing sub-module and a point cloud processing sub-module;
the feature extraction and classification module comprises a deep feature extraction sub-module, a machine learning classification sub-module and a building identification sub-module;
the three-dimensional reconstruction module comprises a point cloud registration sub-module, a segmentation and classification sub-module and a surface reconstruction sub-module;
the multi-target analysis module comprises a structure analysis sub-module, an energy consumption analysis sub-module and a use efficiency analysis sub-module;
the comprehensive report module comprises a building performance analysis sub-module, a potential problem identification sub-module and a building optimization suggestion sub-module.
4. Computer device comprising a memory and a processor, characterized in that the memory has stored therein a computer program which, when executed, implements the steps of the building mapping method according to claim 1.
5. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the building mapping method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311122604.9A CN116844068B (en) | 2023-09-01 | 2023-09-01 | Building mapping method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311122604.9A CN116844068B (en) | 2023-09-01 | 2023-09-01 | Building mapping method, system, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116844068A CN116844068A (en) | 2023-10-03 |
| CN116844068B true CN116844068B (en) | 2023-12-26 |
Family
ID=88171082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311122604.9A Active CN116844068B (en) | 2023-09-01 | 2023-09-01 | Building mapping method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116844068B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117115169A (en) * | 2023-10-25 | 2023-11-24 | 宁波吉烨汽配模具有限公司 | Intelligent recognition method for abnormal deformation of surface of die-casting die of automobile part |
| CN117436033B (en) * | 2023-12-13 | 2024-02-27 | 河北建设集团股份有限公司 | Intelligent building vertical deviation monitoring system and method |
| CN117994460A (en) * | 2024-02-29 | 2024-05-07 | 广东省核工业地质调查院 | Three-dimensional geological refinement modeling method and device based on air-ground combination |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605978A (en) * | 2013-11-28 | 2014-02-26 | 中国科学院深圳先进技术研究院 | Urban illegal building identification system and method based on three-dimensional live-action data |
| CN106779620A (en) * | 2016-12-30 | 2017-05-31 | 广州市凯思软件工程有限公司 | Digitized Design Platform building method based on IPD systems |
| CN109325993A (en) * | 2018-08-10 | 2019-02-12 | 华北电力大学（保定） | A kind of significant characteristics reinforcing method of sampling based on class octree index |
| CN109636911A (en) * | 2018-11-06 | 2019-04-16 | 深圳华侨城文化旅游科技股份有限公司 | A kind of scan method and system based on somatosensory device |
| CN109727308A (en) * | 2017-10-30 | 2019-05-07 | 三纬国际立体列印科技股份有限公司 | The three-dimensional point cloud model generating device and generation method of entity article |
| CN112598796A (en) * | 2020-12-28 | 2021-04-02 | 华东交通大学 | Method for building and automatically updating three-dimensional building information model based on generalized point cloud |
| CN112819135A (en) * | 2020-12-21 | 2021-05-18 | 中国矿业大学 | Sorting method for guiding mechanical arm to grab materials in different poses based on ConvPoint model |
| CN112836260A (en) * | 2021-01-20 | 2021-05-25 | 青岛星邦光电科技有限责任公司 | Three-dimensional mapping and collecting method and system for building foundation structure data |
| CN113177477A (en) * | 2021-04-29 | 2021-07-27 | 湖南大学 | Target detection and identification method based on three-dimensional point cloud analysis |
| CN113362454A (en) * | 2021-06-17 | 2021-09-07 | 浙江理工大学 | Building model generation method based on panoramic three-dimensional image |
| CN113744337A (en) * | 2021-09-07 | 2021-12-03 | 江苏科技大学 | Synchronous positioning and mapping method integrating vision, IMU and sonar |
| CN114089787A (en) * | 2021-09-29 | 2022-02-25 | 航天时代飞鸿技术有限公司 | Ground three-dimensional semantic map based on multi-machine cooperative flight and construction method thereof |
| CN114842139A (en) * | 2022-04-15 | 2022-08-02 | 西安翻译学院 | Building three-dimensional digital model construction method based on spatial analysis |
| CN115761172A (en) * | 2022-10-10 | 2023-03-07 | 哈尔滨工程大学 | Single building three-dimensional reconstruction method based on point cloud semantic segmentation and structure fitting |
| CN115861569A (en) * | 2022-12-06 | 2023-03-28 | 中冶南方城市建设工程技术有限公司 | Three-dimensional reconstruction method based on digital image acquisition in existing building green reconstruction |
| CN116129067A (en) * | 2022-12-23 | 2023-05-16 | 龙岩学院 | Urban live-action three-dimensional modeling method based on multi-source geographic information coupling |
| CN116295279A (en) * | 2023-02-08 | 2023-06-23 | 江西良测信息技术有限公司 | Unmanned aerial vehicle remote sensing-based building mapping method and unmanned aerial vehicle |
| CN116310192A (en) * | 2022-12-28 | 2023-06-23 | 江苏省测绘研究所 | Urban building three-dimensional model monomer reconstruction method based on point cloud |
| CN116341078A (en) * | 2023-03-29 | 2023-06-27 | 苏州筑百年建筑科技有限公司 | Intelligent design and construction cloud platform for assembled building and application |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10127434B2 (en) * | 2016-07-15 | 2018-11-13 | Tyco Fire & Security Gmbh | Techniques for built environment representations |
-
2023
- 2023-09-01 CN CN202311122604.9A patent/CN116844068B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605978A (en) * | 2013-11-28 | 2014-02-26 | 中国科学院深圳先进技术研究院 | Urban illegal building identification system and method based on three-dimensional live-action data |
| CN106779620A (en) * | 2016-12-30 | 2017-05-31 | 广州市凯思软件工程有限公司 | Digitized Design Platform building method based on IPD systems |
| CN109727308A (en) * | 2017-10-30 | 2019-05-07 | 三纬国际立体列印科技股份有限公司 | The three-dimensional point cloud model generating device and generation method of entity article |
| CN109325993A (en) * | 2018-08-10 | 2019-02-12 | 华北电力大学（保定） | A kind of significant characteristics reinforcing method of sampling based on class octree index |
| CN109636911A (en) * | 2018-11-06 | 2019-04-16 | 深圳华侨城文化旅游科技股份有限公司 | A kind of scan method and system based on somatosensory device |
| CN112819135A (en) * | 2020-12-21 | 2021-05-18 | 中国矿业大学 | Sorting method for guiding mechanical arm to grab materials in different poses based on ConvPoint model |
| CN112598796A (en) * | 2020-12-28 | 2021-04-02 | 华东交通大学 | Method for building and automatically updating three-dimensional building information model based on generalized point cloud |
| CN112836260A (en) * | 2021-01-20 | 2021-05-25 | 青岛星邦光电科技有限责任公司 | Three-dimensional mapping and collecting method and system for building foundation structure data |
| CN113177477A (en) * | 2021-04-29 | 2021-07-27 | 湖南大学 | Target detection and identification method based on three-dimensional point cloud analysis |
| CN113362454A (en) * | 2021-06-17 | 2021-09-07 | 浙江理工大学 | Building model generation method based on panoramic three-dimensional image |
| CN113744337A (en) * | 2021-09-07 | 2021-12-03 | 江苏科技大学 | Synchronous positioning and mapping method integrating vision, IMU and sonar |
| CN114089787A (en) * | 2021-09-29 | 2022-02-25 | 航天时代飞鸿技术有限公司 | Ground three-dimensional semantic map based on multi-machine cooperative flight and construction method thereof |
| CN114842139A (en) * | 2022-04-15 | 2022-08-02 | 西安翻译学院 | Building three-dimensional digital model construction method based on spatial analysis |
| CN115761172A (en) * | 2022-10-10 | 2023-03-07 | 哈尔滨工程大学 | Single building three-dimensional reconstruction method based on point cloud semantic segmentation and structure fitting |
| CN115861569A (en) * | 2022-12-06 | 2023-03-28 | 中冶南方城市建设工程技术有限公司 | Three-dimensional reconstruction method based on digital image acquisition in existing building green reconstruction |
| CN116129067A (en) * | 2022-12-23 | 2023-05-16 | 龙岩学院 | Urban live-action three-dimensional modeling method based on multi-source geographic information coupling |
| CN116310192A (en) * | 2022-12-28 | 2023-06-23 | 江苏省测绘研究所 | Urban building three-dimensional model monomer reconstruction method based on point cloud |
| CN116295279A (en) * | 2023-02-08 | 2023-06-23 | 江西良测信息技术有限公司 | Unmanned aerial vehicle remote sensing-based building mapping method and unmanned aerial vehicle |
| CN116341078A (en) * | 2023-03-29 | 2023-06-27 | 苏州筑百年建筑科技有限公司 | Intelligent design and construction cloud platform for assembled building and application |
Non-Patent Citations (4)
| Title |
|---|
| 3D model reconstruction based on multiple view image capture;P. -H. Lee et al;《2012 International Symposium on Intelligent Signal Processing and Communications Systems》;58-63 * |
| BIM技术在能耗分析中的应用――以阜新地区某居住建筑为例;段红玉等;《住宅科技》;第40卷(第9期);27-29+34 * |
| BIM技术支持下的绿色建筑设计思路研究;张宇鹏;《城市建筑》;第17卷(第9期);110-111 * |
| 建设工程造价管理学科的创立与发展（三）---学科的发展;蒋传辉;《工程造价管理》(第2期);82-92 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116844068A (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116844068B (en) | Building mapping method, system, computer equipment and storage medium | |
| EP3452959B1 (en) | Model construction in a neural network for object detection | |
| US11443444B2 (en) | Interior photographic documentation of architectural and industrial environments using 360 panoramic videos | |
| CN110222626B (en) | Unmanned scene point cloud target labeling method based on deep learning algorithm | |
| Cheng et al. | 3D building model reconstruction from multi-view aerial imagery and lidar data | |
| Arayici | Towards building information modelling for existing structures | |
| Yang et al. | Automated extraction of street-scene objects from mobile lidar point clouds | |
| Cheng et al. | BIM applied in historical building documentation and refurbishing | |
| CN110796694A (en) | Fruit three-dimensional point cloud real-time acquisition method based on KinectV2 | |
| CN109961510B (en) | High-cut-slope geological rapid recording method based on three-dimensional point cloud reconstruction technology | |
| CN108711172B (en) | Unmanned aerial vehicle identification and positioning method based on fine-grained classification | |
| CN112613397B (en) | Method for constructing target recognition training sample set of multi-view optical satellite remote sensing image | |
| Bognot et al. | Building construction progress monitoring using unmanned aerial system (UAS), low-cost photogrammetry, and geographic information system (GIS) | |
| Ma et al. | An intelligent object detection and measurement system based on trinocular vision | |
| CN115439621A (en) | Three-dimensional map reconstruction and target detection method for coal mine underground inspection robot | |
| Kukolj et al. | Road edge detection based on combined deep learning and spatial statistics of LiDAR data | |
| Xiao et al. | Monitoring excavation slope stability using drones | |
| Richards-Rissetto et al. | A 3D point cloud Deep Learning approach using Lidar to identify ancient Maya archaeological sites | |
| CN113033386A (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| Zeng et al. | Integrating as-built BIM model from point cloud data in construction projects | |
| Zhan et al. | Objects classification from laser scanning data based on multi-class support vector machine | |
| Ahmed et al. | High-quality building information models (BIMs) using geospatial datasets | |
| Amer et al. | Crowd-sourced visual data collection for monitoring indoor construction in 3d | |
| Jannat et al. | Extracting Ancient Maya Structures from Aerial LiDAR Data using Deep Learning | |
| Che et al. | Road Crack Detection and Recognition Based on Image Correction of Horizontal Camera and Convolutional Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |