File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.46421/2706-6568.37.2020.paper023
- Find via
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Digital twinning of construction objects: Lessons learned from pose estimation methods
Title | Digital twinning of construction objects: Lessons learned from pose estimation methods |
---|---|
Authors | |
Keywords | Digital twin Pose estimation Machine learning Digital construction site Smart construction object |
Issue Date | 2020 |
Publisher | CIB (International Council for Research and Innovation in Building and Construction). The Proceedings' web site is located at https://itc.scix.net/series/w78_2020 |
Citation | The 37th International CIB W78 Conference 2000, Virtual Conference, São Paulo, Brazil, 18-20 August 2020. In Santos, ET & Scheer, S (eds.). Conference Proceedings, p. 327-337 How to Cite? |
Abstract | Productivity and safety in the construction industry have long been hindered by the many uncertainties and lack of awareness in the semi-controlled site environment. The digital twinning of construction objects aims at offering digital replicas with real-time, trustable evidence for automated monitoring, human-centric decision-making, or fully automatic cyber-physical systems. This paper revisits the pose estimation methods for the digital twinning of various on-site construction objects, including construction components, equipment, and humans. From a machine learning perspective, all the pose estimation methods can be categorized into four classes, i.e., filtering, supervised, reinforcement, and unsupervised. The inputs, processes, output, and target objects of each class are introduced with demonstrative cases. Comparisons on the pros and the cons of the methods reveal the best choices for digital twinning under different objectives, such as a safer site and more productive construction, as well as constraints such as pose accuracy, computational time, and overall cost. The complexities of digital twinning different construction objects are compared to explain the distribution of existing cases in the literature. Opportunities and possible research directions in the new era of AI and blockchain are recommended at the end. |
Persistent Identifier | http://hdl.handle.net/10722/284736 |
ISSN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Xue, F | - |
dc.contributor.author | Guo, H | - |
dc.contributor.author | Lu, WW | - |
dc.date.accessioned | 2020-08-07T09:01:56Z | - |
dc.date.available | 2020-08-07T09:01:56Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | The 37th International CIB W78 Conference 2000, Virtual Conference, São Paulo, Brazil, 18-20 August 2020. In Santos, ET & Scheer, S (eds.). Conference Proceedings, p. 327-337 | - |
dc.identifier.issn | 2706-6568 | - |
dc.identifier.uri | http://hdl.handle.net/10722/284736 | - |
dc.description.abstract | Productivity and safety in the construction industry have long been hindered by the many uncertainties and lack of awareness in the semi-controlled site environment. The digital twinning of construction objects aims at offering digital replicas with real-time, trustable evidence for automated monitoring, human-centric decision-making, or fully automatic cyber-physical systems. This paper revisits the pose estimation methods for the digital twinning of various on-site construction objects, including construction components, equipment, and humans. From a machine learning perspective, all the pose estimation methods can be categorized into four classes, i.e., filtering, supervised, reinforcement, and unsupervised. The inputs, processes, output, and target objects of each class are introduced with demonstrative cases. Comparisons on the pros and the cons of the methods reveal the best choices for digital twinning under different objectives, such as a safer site and more productive construction, as well as constraints such as pose accuracy, computational time, and overall cost. The complexities of digital twinning different construction objects are compared to explain the distribution of existing cases in the literature. Opportunities and possible research directions in the new era of AI and blockchain are recommended at the end. | - |
dc.language | eng | - |
dc.publisher | CIB (International Council for Research and Innovation in Building and Construction). The Proceedings' web site is located at https://itc.scix.net/series/w78_2020 | - |
dc.relation.ispartof | ICCCBE/ CIB W78 Joint Conference 2000: 18th ICCCBE (International Conference on Computing in Civil and Building Engineering) & 37th International CIB W78 Virtual Joint Conference | - |
dc.subject | Digital twin | - |
dc.subject | Pose estimation | - |
dc.subject | Machine learning | - |
dc.subject | Digital construction site | - |
dc.subject | Smart construction object | - |
dc.title | Digital twinning of construction objects: Lessons learned from pose estimation methods | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Xue, F: xuef@hku.hk | - |
dc.identifier.email | Lu, WW: wilsonlu@hku.hk | - |
dc.identifier.authority | Xue, F=rp02189 | - |
dc.identifier.authority | Lu, WW=rp01362 | - |
dc.description.nature | link_to_OA_fulltext | - |
dc.identifier.doi | 10.46421/2706-6568.37.2020.paper023 | - |
dc.identifier.hkuros | 312558 | - |
dc.identifier.hkuros | 320538 | - |
dc.identifier.spage | 327 | - |
dc.identifier.epage | 337 | - |
dc.identifier.issnl | 2706-6568 | - |