scholarly journals A geometric deep learning approach for checking element-to-entity mappings in infrastructure building information models

2020 ◽  
Author(s):  
Bonsang Koo ◽  
Raekyu Jung ◽  
Youngsu Yu ◽  
Inhan Kim
Keyword(s):  
Deep Learning ◽  
Point Clouds ◽  
3D Models ◽  
Classification Performance ◽  
Information Modeling ◽  
Data Interoperability ◽  
Industry Foundation Classes ◽  
Domain Specific ◽  
Information Models ◽  
Building Information

Abstract Data interoperability between domain-specific applications is a key prerequisite for building information modeling (BIM) to solidify its position as a central medium for collaboration and information sharing in the construction industry. The Industry Foundation Classes (IFC) provides an open and neutral data format to standardize data exchanges in BIM, but is often exposed to data loss and misclassifications. Concretely, errors in mappings between BIM elements and IFC entities may occur due to manual omissions or the lack of awareness of the IFC schema itself, which is broadly defined and highly complex. This study explored the use of geometric deep learning models to classify infrastructure BIM elements, with the ultimate goal of automating the prechecking of BIM-to-IFC mappings. Two models with proven classification performance, Multi-View Convolutional Neural Network (MVCNN) and PointNet, were trained and tested to classify 10 types of commonly used BIM elements in road infrastructure, using a dataset of 1496 3D models. Results revealed MVCNN as the superior model with ACC and F1 score values of 0.98 and 0.98, compared with PointNet's corresponding values of 0.83 and 0.87, respectively. MVCNN, which employs multiple images to learn the features of a 3D artifact, was able to discern subtle differences in their shapes and geometry. PointNet seems to lose the granularity of the shapes, as it uses points partially selected from point clouds.

scholarly journals ABGS: A System for the Automatic Generation of Building Information Models from Two-Dimensional CAD Drawings

2020 ◽  
Vol 12 (17) ◽  
pp. 6713
Author(s):  
Youngsoo Byun ◽  
Bong-Soo Sohn
Keyword(s):  
Computer Aided Design ◽  
Low Cost ◽  
3D Models ◽  
Automatic Generation ◽  
Information Modeling ◽  
Two Dimensional ◽  
Efficient Design ◽  
Information Models ◽  
Building Information ◽  
Floor Plans

Building Information Modeling (BIM) refers to 3D-based digital modeling of buildings and infrastructure for efficient design, construction, and management. Governments have recognized and encouraged BIM as a primary method for enabling advanced construction technologies. However, BIM is not universally employed in industries, and most designers still use Computer-Aided Design (CAD) drawings, which have been used for several decades. This is because the initial costs for setting up a BIM work environment and the maintenance costs involved in using BIM software are substantially high. With this motivation, we propose a novel software system that automatically generates BIM models from two-dimensional (2D) CAD drawings. This is highly significant because only 2D CAD drawings are available for most of the existing buildings. Notably, such buildings can benefit from the BIM technology using our low-cost conversion system. One of the common problems in existing methods is possible loss of information that may occur during the process of conversion from CAD to BIM because they mainly focus on creating 3D geometric models for BIM by using only floor plans. The proposed method has an advantage of generating BIM that contains property information in addition to the 3D models by analyzing floor plans and other member lists in the input design drawings together. Experimental results show that our method can quickly and accurately generate BIM models from 2D CAD drawings.

scholarly journals Automatic 2D Floorplan CAD Generation from 3D Point Clouds

2020 ◽  
Vol 10 (8) ◽  
pp. 2817 ◽  
Author(s):  
Uuganbayar Gankhuyag ◽  
Ji-Hyeong Han
Keyword(s):  
Point Clouds ◽  
Detection Algorithm ◽  
Information Modeling ◽  
Ongoing Research ◽  
Cloud Data ◽  
Industry Foundation Classes ◽  
Automated Method ◽  
3D Point Clouds ◽  
Building Information ◽  
Geometric Quality

In the architecture, engineering, and construction (AEC) industry, creating an indoor model of existing buildings has been a challenging task since the introduction of building information modeling (BIM). Because the process of BIM is primarily manual and implies a high possibility of error, the automated creation of indoor models remains an ongoing research. In this paper, we propose a fully automated method to generate 2D floorplan computer-aided designs (CADs) from 3D point clouds. The proposed method consists of two main parts. The first is to detect planes in buildings, such as walls, floors, and ceilings, from unstructured 3D point clouds and to classify them based on the Manhattan-World (MW) assumption. The second is to generate 3D BIM in the industry foundation classes (IFC) format and a 2D floorplan CAD using the proposed line-detection algorithm. We experimented the proposed method on 3D point cloud data from a university building, residential houses, and apartments and evaluated the geometric quality of a wall reconstruction. We also offer the source code for the proposed method on GitHub.

scholarly journals A TOOL FOR CROWDSOURCED BUILDING INFORMATION MODELING THROUGH LOW-COST RANGE CAMERA: PRELIMINARY DEMONSTRATION AND POTENTIAL

2017 ◽  
Vol XLII-2/W8 ◽  
pp. 75-81
Author(s):  
F. Capocchiano ◽  
R. Ravanelli ◽  
M. Crespi
Keyword(s):  
Low Cost ◽  
3D Models ◽  
Information Modeling ◽  
Indoor Environments ◽  
Range Camera ◽  
Information Models ◽  
Building Geometry ◽  
3D Geometry ◽  
Building Information ◽  
Geometrical Information

Within the construction sector, Building Information Models (BIMs) are more and more used thanks to the several benefits that they offer in the design of new buildings and the management of the existing ones. Frequently, however, BIMs are not available for already built constructions, but, at the same time, the range camera technology provides nowadays a cheap, intuitive and effective tool for automatically collecting the 3D geometry of indoor environments. It is thus essential to find new strategies, able to perform the first step of the scan to BIM process, by extracting the geometrical information contained in the 3D models that are so easily collected through the range cameras.<br><br> In this work, a new algorithm to extract planimetries from the 3D models of rooms acquired by means of a range camera is therefore presented. The algorithm was tested on two rooms, characterized by different shapes and dimensions, whose 3D models were captured with the Occipital Structure Sensor<sup>TM</sup>. The preliminary results are promising: the developed algorithm is able to model effectively the 2D shape of the investigated rooms, with an accuracy level comprised in the range of 5 - 10 cm. It can be potentially used by non-expert users in the first step of the BIM generation, when the building geometry is reconstructed, for collecting crowdsourced indoor information in the frame of BIMs Volunteered Geographic Information (VGI) generation.

scholarly journals EXTRACTION AND TRANSFORMATION OF IFC DATA TO CITYGML FORMAT

2019 ◽  
Vol XLII-4/W16 ◽  
pp. 595-601 ◽  
Author(s):  
M. J. Sani ◽  
I. A. Musliman ◽  
A. Abdul Rahman
Keyword(s):  
Information Exchange ◽  
Data Exchange ◽  
Transformation Process ◽  
Information Modeling ◽  
Data Interoperability ◽  
Industry Foundation Classes ◽  
Gis Applications ◽  
Two Systems ◽  
Building Information ◽  
The Difference

Abstract. The integration of Geographic Information System (GIS) and the Building Information Modeling (BIM) referred to as the merging of the two systems for the purpose of data interoperability. The need to share information between the two systems is what motivated the integration process purposely for geospatial analysis. This can be achieved through their data exchange formats such as; City Markup Language (CityGML) and Industry Foundation Classes (IFC). The formats are the two most prominent key schemas of GIS and BIM systems respectively. The integration is a step towards information exchange or sharing (data interoperability) between the two systems. The selection of the two most prominent data exchange formats is as a result of their widespread applications in the GIS and BIM domains. However, the differences in geometric and the semantics information hinders data interoperability (information sharing) between GIS and BIM. Also, coupled with the difference in schema structure and the level of information richness between IFC and CityGML. This paper, propose a geometry transformation process that can be used to extract and transform IFC building objects to that of CityGML building objects to enable 3D model design and constructed using BIM tool to be easily reused in 3D GIS applications which will be able to support the CityGML model format. Where the geometric information will be extracted using the IFC tree-structure (hierarchy) and transformed to destination CityGML.

scholarly journals Applying novelty detection to identify model element to IFC class misclassifications on architectural and infrastructure Building Information Models

2018 ◽  
Vol 5 (4) ◽  
pp. 391-400 ◽  
Author(s):  
Bonsang Koo ◽  
Byungjin Shin
Keyword(s):  
Ad Hoc ◽  
Performance Metrics ◽  
Novelty Detection ◽  
Information Modeling ◽  
True Negative ◽  
Industry Foundation Classes ◽  
Information Models ◽  
Building Information ◽  
Superior Approach ◽  
Performance Results

Abstract Ensuring the correct mapping of model elements to Industry Foundation Classes (IFC) classes is fundamental for the seamless exchange of information between Building Information Modeling (BIM) applications, and thus achieve true interoperability. This research explored the possibility of employing novelty detection, a machine learning approach, as a way to detect potential misclassifications that occur during current ad hoc and manual mapping practices. By training the algorithm to learn the geometry of BIM elements for a given IFC class, outliers are detected automatically. A framework for leveraging multiple BIM models and training individual one-class SVM's was formulated and tested on four IFC classes. Performance results demonstrate the classification models to be robust and unbiased. The algorithms developed thus can be leveraged to check the integrity of IFC data, a prerequisite for BIM-based quality control and code compliance. Highlights The correct mapping of BIM elements to IFC classes is critical for IFC based interoperability. A framework is formalized for applying novelty detection to automate the checking of misclassifications. One-class SVM's are trained and tested on two architectural and two infrastructure IFC classes. Performance metrics indicate robust and unbiased models with high accuracy and true negative rates. Novelty detection is a superior approach to outlier detection in identifying misclassifications of BIM to IFC associations.

scholarly journals BUILDING INFORMATION MODELING APPLIED TO THE INDUSTRIAL ARCHITECTURAL MONUMENTS CASE STUDY OF SAINT PETERSBURG

2019 ◽  
Vol XLII-5/W2 ◽  
pp. 59-63
Author(s):  
E. S. Soonwald ◽  
A. E. Wojnarowski ◽  
S. G. Tikhonov ◽  
O. V. Artemeva ◽  
S. V. Tyurin
Keyword(s):  
Research And Development ◽  
Laser Scanning ◽  
Life Cycle Management ◽  
3D Models ◽  
Information Modeling ◽  
Historical Building ◽  
Saint Petersburg ◽  
Information Models ◽  
Building Information ◽  
Building Information Models

<p><strong>Abstract.</strong> Development and implementation of information models of spatial objects affect broadest application areas currently. Building Information Models (BIMs) are now becoming extremely popular. These models are able to describe a great number characteristics of building or engineering construction, including physical and functional properties, economic parameters, visual parameters, etc. BIM use is introduced currently as the mandatory aspect of building life cycle management, from design and construction to demolition. However, implementation of the BIM concept into the reconstruction, restoration and conservation of historical and cultural heritage remains the least developed domain. Therefore, research and development activities concerned with HBIMs (Historical Building Information Models) are particularly relevant. Saint Petersburg being the second largest Russian city has a huge number of architectural monuments, while industrial architecture composes a special category of these monuments. We provided a number of research and development activities devoted to the 3D information modelling of industrial architectural monuments located in St. Petersburg. Context of these works was established by the reconstruction and adaptation of these monuments to modern needs. 3D models of buildings were produced basing on results of the laser scanning and photogrammetric survey. Basing on our work, we have formalized main approaches to design and implementation of Building Information Models of the industrial architectural monuments.</p>

Application of 3D Bridge Information Modeling in the Life-cycle of Bridges

2019 ◽  
Author(s):  
Afshin Hatami ◽  
Alex Mabrich
Keyword(s):  
3D Model ◽  
Structural Model ◽  
New Technology ◽  
3D Models ◽  
Information Modeling ◽  
Design Quality ◽  
Improve Design ◽  
Information Models ◽  
Building Information ◽  
3D Information

<p>Building information modeling (BIM) is a new technology in the bridge construction industry. 3D models can provide perfect numerical expression of drawings from design results. 3D information models for bridge structures improve design quality in terms of accurate drawings, constructability, and collaboration. However, there are lots of challenges to apply these techniques to actual bridge projects. For instance, bridge engineers are facing the challenge of making the vast information generated by their structural model useful for professionals further down the line in the lifecycle of the bridge. Contractors and inspectors require a 3D model which is created after the design process to add extra information related to activities and store that information in the same model. In this paper, technologies available to generate, manage, and enrich the bridge 3D model with intelligent information from construction to design and inspection are proposed.</p>

scholarly journals Design of Railway Track Model with Three-Dimensional Alignment Based on Extended Industry Foundation Classes

2020 ◽  
Vol 10 (10) ◽  
pp. 3649
Author(s):  
Tae Ho Kwon ◽  
Sang I. Park ◽  
Young-Hoon Jang ◽  
Sang-Ho Lee
Keyword(s):  
Classification System ◽  
Building Information Modeling ◽  
Three Dimensional ◽  
Software Tools ◽  
Information Modeling ◽  
Railway Track ◽  
Industry Foundation Classes ◽  
Information Models ◽  
Building Information ◽  
Track Test

Building information modeling (BIM) has been widely applied in conjunction with the industry foundation class (IFC) for buildings and infrastructure such as railways. However, a limitation of the BIM technology presents limitations that make designing the three-dimensional (3D) alignment-based information models difficult. Thus, the time and effort required to create a railway track model are increased, while the reliability of the model is reduced. In this study, we propose a methodology for developing an alignment-based independent railway track model and extended IFC models containing railway alignment information. The developed algorithm using BIM software tools allows for a discontinuous structure to be designed. The 3D alignment information connects different BIM software tools, and the classification system and IFC schema for expressing railway tracks are extended. Moreover, the classification system is fundamental for assigning IFC entities to railway components. Spatial and hierarchical entities were created through a developed user interface. The proposed methodology was implemented in an actual railway track test. The possibility of managing IFC-based railway track information, including its 3D alignment information, was confirmed. The proposed methodology can reduce the modeling time and can be extended to other alignment-based structures, such as roads.

scholarly journals POINT CLOUD BASED 3D MODELS FOR AGENT BASED SIMULATIONS IN SOCIAL DISTANCING AND EVACUATION

2021 ◽  
Vol V-4-2021 ◽  
pp. 113-120
Author(s):  
S. Nikoohemat ◽  
P. Godoy ◽  
N. Valkhoff ◽  
M. Wouters - van Leeuwen ◽  
R. Voûte ◽  
...  
Keyword(s):  
Point Clouds ◽  
3D Models ◽  
Raw Material ◽  
Agent Based ◽  
Social Distancing ◽  
Information Models ◽  
Mapping System ◽  
Agent Based Simulations ◽  
Building Information ◽  
Mobile Mapping System

Abstract. Point clouds serve as the raw material for various models, such as Building Information Models (BIM). In this work, we investigate the reconstruction steps needed to create models that can be utilized directly for agent-based simulations. The input data for the reconstruction is captured with an indoor mobile mapping system. To show the prominence of this idea, we run social distancing and evacuation simulations on the reconstructed models. The simulations are run with multiple agents using a vision-based pedestrian model and A*-based path finding algorithm. The limitations of this approach are discussed. The video of the simulation is shared with the audience.Link to the video: https://youtu.be/r2D3IxXt7Ls

Sign in / Sign up

Export Citation Format

Share Document