Methods for the Automated Assignment and Comparison of Building Damage Geometries

Taraben, Jakob; Morgenthal, Guido

doi:10.1016/j.aei.2020.101186

Cited by 26 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, as point clouds produced by SfM are up‐to‐scale and have an undetermined georeferenced system, precise quantitative information on the defects is absent. To cope with the limitation, existing studies either leverage pre‐deployed markers (Hamdan et al., 2021; Lin et al., 2021) or 3D models (Isailović et al., 2020; Taraben & Morgenthal, 2021) as a reference to adjust the point clouds. Lin et al.…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, point clouds generated based on SfM are up to scale and have undetermined reference frames. As a result, manual efforts are required to either register the point cloud to a reference model (Isailović et al., 2020; Taraben & Morgenthal, 2021) or use dedicated markers to transform the model to correct geolocations (Hamdan et al., 2021; Lin et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic concrete defect detection and reconstruction by aligning aerial images onto semantic‐rich building information model

Chen

Lou

2022

Computer aided Civil Eng

View full text Add to dashboard Cite

Concrete defect information is of vital importance to building maintenance. Increasingly, computer vision has been explored for automated concrete defect detection. However, existing studies suffer from the challenging issue of false positives. In addition, 3D reconstruction of the defects to pinpoint their positions and geometries has not been sufficiently explored. To address these limitations, this study proposes a novel computational approach for detecting and reconstructing concrete defects from geotagged aerial images. A bundle registration algorithm is devised to align a batch of aerial photographs with a building information model (BIM). The registration enables the retrieval of material semantics in BIM to determine the regions of interest for defect detection. It helps rectify the camera poses of the aerial images, enabling precise defect reconstruction.Experiments demonstrate the effectiveness of the approach, which significantly reduced the false discovery rate from 70.8% to 56.8%, resulting in an intersection over union 6.4% higher than that of the traditional method. The geometry of the defects was successfully reconstructed in 3D world space. This study opens a new avenue to advance the field of defect detection by exploiting the rich information from BIM. The approach can be deployed at scale, supporting urban renovation, numerical simulation, and other smart applications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic concrete defect detection and reconstruction by aligning aerial images onto semantic‐rich building information model

Chen

Lou

2022

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…Zentrale Aspekte der Verwaltung von Zustandsdaten im beschriebenen Metamodell sind die Verknüpfung und der automatisierte Vergleich unterschiedlicher Zustandsauf- [22] (green -already annotated domain, red -section added in the state) for t 1 -t 6 , (C) annotations of the identical crack in states t 1 -t 6 and generated evaluation of the crack length and crack growth from automated comparison…”

Section: Beschreibung Von Zustandsvergleichenunclassified

Datenmodelle für digitale Zwillinge von Brücken und bildbasierte Zustandsaufnahmen

2022

Self Cite

View full text Add to dashboard Cite

Für eine präventive und nachhaltige Instandhaltung von Infrastrukturbauwerken sind regelmäßige visuelle Inspektionen von großer Bedeutung, um Schäden frühzeitig zu erkennen und entsprechende Maßnahmen zu ergreifen. Moderne Technologien wie unbemannte Flugsysteme, ausgerüstet mit hochauflösenden Kameras, unterstützen immer mehr den Inspektionsprozess und die damit verbundene Dokumentation. Dadurch entstehen große Mengen an Bilddaten, Orthofotos, Punktwolken und Oberflächennetzen, welche die gesamte Bauwerksoberfläche in einem ausreichend hohen Detailgrad darstellen und die Annotation von visuell detektierbaren Anomalien ermöglichen. Um diese Datenmenge effektiv nutzen und verwalten zu können, sind Methoden zur Verarbeitung und entsprechend verknüpfte Datenmodelle notwendig. Vor dem Hintergrund einer kontinuierlich zu wiederholenden Bauwerksüberwachung ist eine Automatisierung der einzelnen Analyseschritte besonders vielversprechend. In diesem Aufsatz werden Ansätze für die Verarbeitung großer bildbasierter Datensätze zu einem verknüpften Inspektionsmodell beschrieben. Dazu wird gezeigt, wie Annotationen in Bildern und Orthofotos im Kontext von idealisierten Simulationsmodellen genutzt werden und den Prozess der Zustandsbewertung unterstützen können. Der daraus entstehende digitale Zwilling soll eine konsistente Datenbasis über mehrere Zustände abbilden und damit die Verwaltung heterogener Inspektionsdaten ermöglichen.

show abstract

“…Yang et al (2016). create a binary image to detect "holes" in the image Taraben & Kraemer (2021) use a deep learning approach to map the detected windows from 2D images on a previously generated surface model. Schneider & Coors (2018) recognize windows directly in the point cloud using a contouring algorithm.…”

Section: Object Classification: Window Classificationmentioning

confidence: 99%

Retrofitting Potential of Building envelopes Based on Semantic Surface Models Derived From Point Clouds

Selimovic

Noichl

Forth³

et al. 2022

JFDE

View full text Add to dashboard Cite

To meet the climate goals of the Paris agreement, the focus on energy efficiency needs to be shifted to increase the retrofitting rate of the existing building stock. Due to the lack of usable information on the existing building stock, reasoning about the retrofitting potential in early design stages is difficult. Therefore, deconstructing and building new is often regarded as the more reliable and economical option. Digital methods are missing or not robust enough to capture and reconstruct digital models of existing buildings efficiently and automatically derive reliable decision-support about whether demolition and new construction or retrofitting of existing buildings is more suitable. This paper proposes a robust, automated method for calculating existing buildings' life cycle assessments (LCA) using point clouds as input data. The main focus lies in bridging the gap between point clouds and importing semantic 3D models for LCA calculation. Therefore, the automation steps include a geometric transformation from point cloud to 3D surface model, followed by a semantic classification of the surfaces to thermal layers and their materials by assuming the surface elements by building age class.

show abstract

Methods for the Automated Assignment and Comparison of Building Damage Geometries

Cited by 26 publications

References 21 publications

Automatic concrete defect detection and reconstruction by aligning aerial images onto semantic‐rich building information model

Automatic concrete defect detection and reconstruction by aligning aerial images onto semantic‐rich building information model

Datenmodelle für digitale Zwillinge von Brücken und bildbasierte Zustandsaufnahmen

Retrofitting Potential of Building envelopes Based on Semantic Surface Models Derived From Point Clouds

Contact Info

Product

Resources

About