Show simple item record

dc.contributor.authorAssadzadeh, Amin
dc.contributor.authorArashpour, Mehrdad
dc.contributor.authorBrilakis, Ioannis
dc.contributor.authorNgo, Tuan
dc.contributor.authorKonstantinou, Erini
dc.date.accessioned2021-12-11T00:31:26Z
dc.date.available2021-12-11T00:31:26Z
dc.date.issued2022-02
dc.identifier.issn0926-5805
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/331345
dc.description.abstractThe ability to monitor and track the interactions between construction equipment and workers can lead to creating a safer and more productive work environment. Most recent studies employ computer vision and deep learning techniques, which rely on the size and quality of the training datasets for optimal performance. However, preparation of large datasets with high quality annotations remains a manual and time-consuming process. To overcome this challenge, this study presents a framework for synthetically generating large and accurately annotated images. The contribution of this paper is manifold: First, a method is developed using a game engine, which employs domain randomization (DR) to produce large labelled datasets for excavator pose estimation. Second, a state-of-the-art deep learning architecture based on high representation network is adapted and modified for excavator pose estimation. This model is trained on synthetically generated datasets and its performance is evaluated. The results reveal that the model trained on synthetic data can yield comparable results to the model trained on real images of excavators. This demonstrates the effectiveness of utilizing synthetic datasets for complex vision tasks such as equipment pose estimation. The study concludes by highlighting directions for further work in synthetic data studies in construction.
dc.publisherElsevier BV
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.titleVision-based excavator pose estimation using synthetically generated datasets with domain randomization
dc.typeArticle
dc.publisher.departmentDepartment of Engineering
dc.date.updated2021-12-10T10:49:11Z
prism.endingPage104089
prism.number104089
prism.publicationDate2022
prism.publicationNameAutomation in Construction
prism.startingPage104089
prism.volume134
dc.identifier.doi10.17863/CAM.78793
dcterms.dateAccepted2021-12-01
rioxxterms.versionofrecord10.1016/j.autcon.2021.104089
rioxxterms.versionAM
dc.contributor.orcidBrilakis, Ioannis [0000-0003-1829-2083]
rioxxterms.typeJournal Article/Review
pubs.funder-project-idEuropean Commission (334241)
pubs.funder-project-idLeverhulme Trust (IAF-2018-011)
pubs.funder-project-idAustralian Research Council (DP170104613)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Industrial Leadership (IL) (958398)
cam.issuedOnline2021-12-09
cam.orpheus.success2021-12-10 - Embargo set during processing via Fast-track
cam.depositDate2021-12-10
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2022-12-09


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 International
Except where otherwise noted, this item's licence is described as Attribution-NonCommercial-NoDerivatives 4.0 International