Automated semantic segmentation of bridge point cloud based on local descriptor and machine learning

Xia, Tian; Yang, Jian; Chen, L.

doi:10.1016/j.autcon.2021.103992

Cited by 58 publications

(22 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The experimental results show an improvement in the overall accuracy of the proposed method for segmenting bridge members from point cloud data, with an improvement of about 3% in mIoU. Xia et al 86 proposed an automatic semantic segmentation method for bridge point clouds based on local descriptors and machine learning. It selects a custom multi-scale local descriptor for each point in the point cloud to train a deep classification neural network.…”

Section: Point Cloud Data-oriented Methodsmentioning

confidence: 97%

Review of artificial intelligence-based bridge damage detection

Zhang

Yuen

2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Bridges are often located in harsh environments and are thus extremely susceptible to damage. If the initial damage is not detected in time, it can develop further causing safety hazards. Therefore, accurate detection of bridge damage is an important topic. In recent years, artificial intelligence technology has been developed rapidly, especially machine learning algorithms, which have shown amazing results in various fields while it also received attention in bridge inspection. This paper summarizes the progress of bridge damage detection research related to artificial intelligence techniques between 2015 and 2021. For structural health monitoring, sensing data is the basis for various data processing methods. The strength and weakness of the sensing data itself directly affect the effectiveness of subsequent processing methods. As a result, this paper classifies bridge damage detection studies into six categories from the types of sensing data: visual image, point cloud, infrared thermal imaging, ground-penetrating radar, vibration response, and other types of data. These six types of damage detection methods were reviewed and summarized respectively. Finally, challenges and future trends were discussed.

show abstract

Section: Point Cloud Data-oriented Methodsmentioning

confidence: 97%

Review of artificial intelligence-based bridge damage detection

Zhang

Yuen

2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…B. mit den in Abschn. 3 beschriebenen künstlichen neuronalen Netzen durchführbar [17–20]. Ein großer Nachteil bzw.…”

Section: Anwendungsbeispiel Brückeunclassified

Digitalisierung von Bestandsbauwerken mit KI

2022

View full text Add to dashboard Cite

Der Zustand eines Bauwerks ist dadurch gekennzeichnet, dass er sich mit zunehmendem Alter immer schneller verschlechtert. Eine vorbeugende Maßnahme gegen die Alterung ist umso erfolgreicher, je früher sie ergriffen wird. Um die Nutzung komplexer Bauwerke zu verlängern, sind umfassende Informationen zu einem möglichst frühen Zeitpunkt erforderlich. Auf dem Weg zu einer vorausschauenden Instandhaltung ist Grundlagenforschung zu den Methoden der Erfassung, Zusammenführung und Auswertung aller Geometrie‐, Material‐, Spannungs‐ und Alterungsdaten erforderlich. Die Digitalisierung im Sinne der Erzeugung eines Digitalen Zwillings erhält in diesem Zusammenhang eine völlig neue Bedeutung. Sie ermöglicht die Zusammenführung und Echtzeitauswertung aller für Betrieb und Instandhaltung erforderlichen Daten. Die Bauwirtschaft steht hier jedoch vor besonderen Herausforderungen. Bauwerke, insbesondere in der Verkehrsinfrastruktur, sind einzigartige Objekte. Sie zeichnen sich durch enorme Dimensionen aus und haben eine wesentlich längere Lebensdauer als andere technische Anlagen. Die Veränderungen im Sinne einer Zustandsverschlechterung sind sehr gering und daher kaum messbar. Die Basis eines umfassenden Zustandsmonitorings ist eine umfassende und komplette digitale Repräsentation des Bauwerks. Dies bedeutet eine Abbildung der kompletten äußeren und inneren Struktur in einer digitalen Form, inkl. Informationen zu Materialien, Schadstellen etc. Daraus lässt sich die Forschungsfrage ableiten, ob sich eine solche Abbildung effizient umsetzen lässt und in welcher Form und mit welchen Methoden dies möglich ist. Der vorliegende Beitrag gibt einen Überblick, wie die Umsetzung auch für komplexe Objekte gelingt und wie das generierte Modell mit semantischer Information angereichert werden kann.

show abstract

“…The exploitation of results from millions of points that can be efficiently gathered at the asset site becomes a bottleneck. Attempts on providing automated extraction, identification and use of geometries based on point clouds have been presented in the realm of bridges [8][9][10] and of buildings [11][12][13]. The measurements Laser scanners, also referred as LiDAR (Light Detection and Ranging) are devices that emit narrow, intense beams of coherent monochromatic light for measuring distances to objects.…”

Section: Point Clouds and The Bridgementioning

confidence: 99%

Geometrical Digital Twinning of a Tapered, Horizontally Curved Composite Box Girder Bridge

Chacón¹,

Ramonell²,

Puig‐Polo³

et al. 2022

ce papers

View full text Add to dashboard Cite

A composite bridge located in the Metropolitan Area of Barcelona represents one of the sites for demonstrating the capabilities of digital twins on maintenance of built assets. Digital twins can be deemed to as digital living replica of the physical one that provides real time information throughout adequate connectivity (sensors, images, remote sensing) and provides automated visualization of the asset for decision‐making purposes (performance indicators that are assessed regularly). This demonstrator is an 846 meters long composite bridge with plates and a concrete slab. The plates are tapered along a portion of its length. The bridge is horizontally curved with a bifurcation at its end. One of the challenges in this demonstrator is to reproduce realistically the “as built” shape of the plates using a terrestrial laser scanner for simulation purposes. The outcome of this specific side of the digital twinning (other sides also include many sensor‐ and image‐based methods) is of great interest for maintenance managers. Understanding the real configuration of the asset represents an accurate starting point for subsequent modelling.

show abstract

Automated semantic segmentation of bridge point cloud based on local descriptor and machine learning

Cited by 58 publications

References 65 publications

Review of artificial intelligence-based bridge damage detection

Review of artificial intelligence-based bridge damage detection

Digitalisierung von Bestandsbauwerken mit KI

Geometrical Digital Twinning of a Tapered, Horizontally Curved Composite Box Girder Bridge

Contact Info

Product

Resources

About