Show simple item record

dc.contributor.authorMirzazade, Ali
dc.contributor.authorPopescu, Cosmin
dc.contributor.authorGonzalez-Libreros, Jaime
dc.contributor.authorBlanksvärd, Thomas
dc.contributor.authorTäljsten, Björn
dc.contributor.authorSas, Gabriel
dc.date.accessioned2023-04-20T13:02:16Z
dc.date.available2023-04-20T13:02:16Z
dc.date.created2023-04-04T11:10:06Z
dc.date.issued2023
dc.identifier.citationJournal of Civil Structural Health Monitoring (JCSHM). 2023, .
dc.identifier.issn2190-5452
dc.identifier.urihttps://hdl.handle.net/11250/3064074
dc.description.abstractBridge inspections are relied heavily on visual inspection, and usually conducted within limited time windows, typically at night, to minimize their impact on traffic. This makes it difficult to inspect every meter of the structure, especially for largescale bridges with hard-to-access areas, which creates a risk of missing serious defects or even safety hazards. This paper presents a new technique for the semi-automated damage detection in tunnel linings and bridges using a hybrid approach based on photogrammetry and deep learning. The first approach involves using photogrammetry to reconstruct a 3D model. It is shown that a model with sub-centimeter accuracy can be obtained after noise removal. However, noise removal also reduces the point cloud density, making the 3D point cloud unsuitable for quantification of small-scale damages such as fine cracks. Therefore, the captured images are also analysed using deep convolutional neural network (CNN) models to enable crack detection and segmentation. For this aim, in the second approach, the 3D model is generated by the output of CNN models to enable crack localization and quantification on 3D digital model. These two approaches were evaluated in separate case studies, showing that the proposed technique could be a valuable tool to assist human inspectors in detecting, localizing, and quantifying defects on concrete structures.
dc.description.abstractSemi‑autonomous inspection for concrete structures using digital models and a hybrid approach based on deep learning and photogrammetry
dc.language.isoeng
dc.subjectPhotogrammetry
dc.subjectPhotogrammetry
dc.subjectComputer vision
dc.subjectComputer vision
dc.subjectDamage detection
dc.subjectDamage detection
dc.subjectBridge inspection
dc.subjectBridge inspection
dc.titleSemi‑autonomous inspection for concrete structures using digital models and a hybrid approach based on deep learning and photogrammetry
dc.title.alternativeSemi‑autonomous inspection for concrete structures using digital models and a hybrid approach based on deep learning and photogrammetry
dc.typePeer reviewed
dc.typeJournal article
dc.description.versionpublishedVersion
dc.subject.nsiVDP::Teknologi: 500
dc.subject.nsiVDP::Technology: 500
dc.source.pagenumber20
dc.source.journalJournal of Civil Structural Health Monitoring (JCSHM)
dc.identifier.doi10.1007/s13349-023-00680-x
dc.identifier.cristin2139348
dc.relation.projectAndre: EU Horizon, Shift2Rail. No.101012456. IN2TRACK3
dc.relation.projectAndre: LTU - funding open access
dc.relation.projectAndre: FORMAS, no. 2019-01515
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record