Fully automated methodology for the delineation of railway lanes and the generation of IFC alignment models using 3D point cloud data

Soilán, Mario; Andrea, Nóvoa,; Sánchez‐Rodríguez, Ana; Justo, Andrés; Riveiro, Belén

doi:10.1016/j.autcon.2021.103684

Cited by 33 publications

(26 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The use of new technologies for infrastructure design and management can improve the network performance while decreasing maintenance risks and costs (Costin et al, 2018). The design process of railway networks could start from survey data, in particular from point-cloud data, defining a methodology to automate railway masts detection from airborne LiDAR (Barazzetti et al, 2020) and then export in IFC format (Ariyachandra and Brilakis, 2020), as well as describing a Cloud-to-IFC workflow that extract rails from 3D point-cloud data and generates IFC files (Soilán et al, 2021). The 'reverse engineering' approach and international standards are also used to model a railway underpass in Slovenia (Abbondati et al, 2020), comparing different BIM-based tools to highlight pros and cons (Biancardo et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

IFCALIGNMENT FOR RASTER-TO-VECTOR GIS RAILWAY CENTRELINE: A CASE STUDY IN THE SOUTH OF ITALY

Garramone

Scaioni²

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Built environment Asset Management (AM) is evolving and renewing itself through the development of new technologies. Building Information Modelling (BIM) is the main methodology for the digitisation process of existing data and information. Although BIM was originally intended for buildings, in the last few years Infrastructure Building Information Modelling (I-BIM) and Civil Information Modelling (CIM) are emerging to manage civil infrastructure. The interaction of infrastructure with the surrounding environment is a fundamental aspect and it requires data-sharing between different sources and systems. Geographic Information Systems (GIS) is used to store and elaborate Earth’s surface information, and it is, therefore, necessary to achieve a complete BIM/GIS interoperability. This paper aims to test the popular BIM open-standard Industry Foundation Classes (IFC) capabilities and potentialities in storing GIS data. A case study of a disused railway in the south of Italy was used to test the methodology presented: rail-centreline (alignment) extraction from GIS raster data, and a conversion of the alignment to an IFCAlignment element. The possibility to export a rail alignment in IFC was confirmed.

show abstract

Section: Discussionmentioning

confidence: 99%

IFCALIGNMENT FOR RASTER-TO-VECTOR GIS RAILWAY CENTRELINE: A CASE STUDY IN THE SOUTH OF ITALY

Garramone

Scaioni²

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The collected numbers of points per class and dataset are collected in Figure 7a,b. As depicted in Figure 7a, the distribution of points over the various classes is quite imbalanced, which is challenging for applying machine learning algorithms but very common for point cloud scenes, as can be seen in similar experiments (J. W. Ma et al, 2020;Soilán et al, 2021). The class analysis is omitted for the factory hall dataset to keep the study concise.…”

Section: Datasetsmentioning

confidence: 99%

Enhancing point cloud semantic segmentation in the data‐scarce domain of industrial plants through synthetic data

Noichl,

Collins,

Braun

et al. 2024

Computer aided Civil Eng

View full text Add to dashboard Cite

Digitizing existing structures is essential for applying digital methods in architecture, engineering, and construction. However, the adoption of data‐driven techniques for transforming point cloud data into useful digital models faces challenges, particularly in the industrial domain, where ground truth datasets for training are scarce. This paper investigates a solution leveraging synthetic data to train data‐driven models effectively. In the investigated industrial domain, the complex geometry of building elements often leads to occlusions, limiting the effectiveness of conventional sampling‐based synthetic data generation methods. Our approach proposes the automatic generation of realistic and semantically enriched ground truth data using surface‐based sampling methods and laser scan simulation on industry‐standard 3D models. In the presented experiments, we use a neural network for point cloud semantic segmentation to demonstrate that compared to sampling‐based alternatives, simulation‐based synthetic data significantly improve mean class intersection over union performance on real point cloud data, achieving up to 7% absolute increase.

show abstract

“…However, BIM was developed based on storey organization, typical of a generic building, and therefore it presents many limitations and issues with respect to alignment-based concepts with reference to transport infrastructure (e.g., railways and roads) [23]. Through the use of photogrammetric techniques, beginning with point clouds, and considering the IFC standard, Soilán et al [24] have developed a solution that involves generating the alignment of the railway infrastructure from the data obtained from the survey (point clouds, etc.). Currently, however, the applications of openBIM, especially in relation to the O&M phases in the case of the railway sector, are limited.…”

Section: Literature Review Application Of Openbim Approach To the Man...mentioning

confidence: 99%

Application of openBIM for the Management of Existing Railway Infrastructure: Case Study of the Cancello–Benevento Railway Line

et al. 2022

View full text Add to dashboard Cite

In the field of infrastructure, the development and application of the openBIM (open Building Information Modeling) approach and related standards (principally Industry Foundation Classes) remain limited with regard to processes in O&M (Operation and Maintenance) phases, as well as the broader context of AM (Asset Management). This article deals with the activities carried out as part of a pilot project based on the need to manage the operation and assess the condition and value of existing infrastructure along the Cancello–Benevento railway line. The principal goal was to systematize information by digitalizing the infrastructure, in order to enable the assessment of possible performance gaps (compared to national railway standards) in the event of integration within the national infrastructure. In compliance with the project requirements, a digitalization strategy was designed for the definition of surveying activities and the implementation of openBIM systems for the development of an object library and a federated digital model, structured within the collaborative platform that was used, and allowing management, maintenance, and subsequent financial evaluation in the broader context of asset management. The project involved the collaboration of railway operators, a university, and a software company that implemented innovative concepts concerning IFC (specifically, IFC4x2 was used) through the development of dedicated software solutions. The digital solution we proposed enabled the use of digital models as access keys to survey and maintenance information (ERP platforms used by the railway operators) that was available in real time. This project was nominated at the buildingSMART awards 2021 and was one of three finalists in the “Asset Management Using openBIM” category.

show abstract

Fully automated methodology for the delineation of railway lanes and the generation of IFC alignment models using 3D point cloud data

Cited by 33 publications

References 18 publications

IFCALIGNMENT FOR RASTER-TO-VECTOR GIS RAILWAY CENTRELINE: A CASE STUDY IN THE SOUTH OF ITALY

IFCALIGNMENT FOR RASTER-TO-VECTOR GIS RAILWAY CENTRELINE: A CASE STUDY IN THE SOUTH OF ITALY

Enhancing point cloud semantic segmentation in the data‐scarce domain of industrial plants through synthetic data

Application of openBIM for the Management of Existing Railway Infrastructure: Case Study of the Cancello–Benevento Railway Line

Contact Info

Product

Resources

About