kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Identifying roadside objects in mobile laser scanning data using image-based point cloud segmentation
KTH, School of Architecture and the Built Environment (ABE), Real Estate and Construction Management, Geodesy and Satellite Positioning.ORCID iD: 0000-0001-9032-4305
KTH, School of Architecture and the Built Environment (ABE), Real Estate and Construction Management, Geodesy and Satellite Positioning.ORCID iD: 0000-0003-0382-9183
2020 (English)In: Journal of Information Technology in Construction, E-ISSN 1874-4753, Vol. 25, p. 545-560Article in journal (Refereed) Published
Abstract [en]

Capturing geographic information from a mobile platform, a method known as mobile mapping, is today one of the best methods for rapid and safe data acquisition along roads and railroads. The digitalization of society and the use of information technology in the construction industry is increasing the need for structured geometric and semantic information about the built environment. This puts an emphasis on automatic object identification in data such as point clouds. Most point clouds are accompanied by RGB images, and a recent literature review showed that these are possibly underutilized for object identification. This article presents a method (image-based point cloud segmentations - IBPCS) where semantic segmentation of images is used to filter point clouds, which drastically reduces the number of points that have to be considered in object identification and allows simpler algorithms to be used. An example implementation where IBPCS is used to identify roadside game fences along a country road is provided, and the accuracy and efficiency of the method is compared to the performance of PointNet, which is a neural network designed for end-to-end point cloud classification and segmentation. The results show that our implementation of IBPCS outperforms PointNet for the given task. The strengths of IBPCS are the ability to filter point clouds based on visual appearance and that it efficiently can process large data sets. This makes the method a suitable candidate for object identification along rural roads and railroads, where the objects of interest are scattered over long distances.

Place, publisher, year, edition, pages
International Council for Research and Innovation in Building and Construction , 2020. Vol. 25, p. 545-560
Keywords [en]
Object identification, Point clouds, Mobile mapping, Laser scanning, Deep learning
National Category
Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:kth:diva-289529DOI: 10.36680/j.itcon.2020.031ISI: 000605615000001Scopus ID: 2-s2.0-85099292194OAI: oai:DiVA.org:kth-289529DiVA, id: diva2:1525162
Note

QC 20210203

Available from: 2021-02-03 Created: 2021-02-03 Last updated: 2025-02-07Bibliographically approved
In thesis
1. Model and Reality: Connecting BIM and the Built Environment
Open this publication in new window or tab >>Model and Reality: Connecting BIM and the Built Environment
2021 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The adoption of building information modeling (BIM) in the architecture, engineering, and construction (AEC) industry is changing the way informa-tion regarding the built environment is created, stored, and exchanged. In short, documents are replaced with databases, processes are automated, and timelines become more circular with an emphasis on managing the life cycles of all manufactured objects. This has both direct and indirect consequences for the fields of geodesy and geographic information. Although geodesy and surveying have played a vital role in the construction process for a long time, new data standards and higher degrees of prefabrication and automation in the actual construction means that the topic of georeferencing must be revisited. In addition, using object oriented data structures means that semantic information must be inferred from geodata such as point clouds and images in order to adequately document existing assets. This thesis addresses the handling of 3D spatial information by analyzing different georeferencing methods and metadata used to describe the quality and characteristics of geodata.The outcomes include a recommendation for how the open BIM standard Industry Foundation Classes (IFC) could be extended to support more robust georeferencing, a suggestion that all standards and exchange formats used forthe built environment should include metadata for tolerance and uncertainty, and a framework that can describe characteristics of 3D spatial data that are not covered by conventional geographic metadata. On the semantic side, this thesis proposes an image-based method for identifying roadside objects in mobile laser scanning (MLS) point clouds, and it also explores the possibilities to train neural networks for point cloud segmentation by creating training data from 3D mesh models used in infrastructure design. Overall, the thesis describes the connection between model and reality, the importance of geodesy and geodetic surveying in this context, and makes contributions to both the geometric and semantic aspects of modeling the built environment.

Abstract [sv]

Införandet av building information modeling (BIM) påverkar informationshanteringen för alla skeden inom den byggda miljöns livscykel; från projektering och konstruktion till underhåll och slutligen avveckling. I korthet är syftet med BIM att ersätta dokumentbaserad kommunikation med modeller, databaser och automatiserade processer. Detta har både direkta och indirekta konsekvenser för områdena geodesi och geoinformatik. Geodesi har länge haft en viktig roll inom byggprocessen, och detta är inget som ändras av BIM-införandet. Nya standarder och mer automatiserade arbetssätt ger dock frågor kring georeferering och geodetiska metadata förnyad relevans. Utöver det så kräver ett objektorienterat arbetssätt att semantik kan utläsas ur insamlade geodata för att möjliggöra modellering av existerande byggnadsverk och anläggningar. I den här avhandlingen analyseras olika georefereringsmetoder samt de metadata som vanligtvis används för att beskriva geodatakvalitet. Resultaten visar att den öppna BIM-standarden Industry Foundation Classes (IFC) kan utökas för att möjliggöra mer robust georeferering. Flertalet standarder som hanterar spatiala data för den byggda miljön saknar också möjlighet att uttrycka kvalitetsmåtten tolerans och osäkerhet. Avhandlingen presenterar även ett ramverk som kan beskriva geometriska egenskaper hos 3D spatiala data som inte täcks av traditionella metadata. På den semantiska sidan presenterar avhandlingen en bildbaserad metod för objektigenkänningi punktmoln framställda genom mobil laserskanning (MLS). Den utforskar även möjligheterna att träna neurala nätverk för punktmolnssegmentering genom att skapa träningsdata från 3D-modeller som används vid projektering. Sammanfattningsvis beskriver avhandlingen hur geodesi och mätningsteknik utgör kopplingen mellan modell och verklighet. Denna koppling innehållerbåde geometri och semantik, och avhandlingen bidrar till den tekniska utvecklingen inom bägge områden.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2021. p. 64
Series
TRITA-ABE-DLT ; 2124
National Category
Other Civil Engineering
Research subject
Geodesy and Geoinformatics, Geodesy
Identifiers
urn:nbn:se:kth:diva-294087 (URN)978-91-7873-892-2 (ISBN)
Public defence
2021-06-04, Videolänk https://kth-se.zoom.us/j/68096006113, Du som saknar dator /datorvana kontakta Milan Horemuz milan.horemuz@abe.kth.se / Use the e-mail address if you need technical assistance, Stockholm, 09:00 (English)
Opponent
Supervisors
Funder
Swedish Transport Administration, FUD 6240
Note

QC 20210511

Available from: 2021-05-11 Created: 2021-05-07 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Uggla, GustafHoremuz, Milan

Search in DiVA

By author/editor
Uggla, GustafHoremuz, Milan
By organisation
Geodesy and Satellite Positioning
In the same journal
Journal of Information Technology in Construction
Computer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 164 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf