Repository logo
 

Generation of Bridge Geometric Digital Twin from Labelled Point Clusters

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Lu, Ruodan 

Abstract

The time required for generating a Geometric Digital Twin of an existing bridge from Point Cloud Data is roughly ten times greater than that needed to laser scan it. There is a pressing need to automate the Point Cloud-to-Geometric Digital Twin process which consists of two major steps: (1) detection of bridge objects in point clouds; and (2) fitting of 3D solid models using Industry Foundation Classes format. Whilst the first step has been automated using existing methods, the second step remains unsolved. The challenges exhibited in the fitting step are due to the irregular geometries of existing bridges. Existing methods have attempted to fit geometric primitives such as cuboids and cylinders that make up a bridge. However, the produced geometric digital twins are too ideal to depict the real geometry of bridges. In addition, none of the existing methods have evaluated the resulting models in terms of spatial accuracy with quantitative measurements. We tackle these challenges by delivering a slicing-based object fitting method that can generate the geometric digital twin of an existing reinforced concrete bridge based on quantitative metrics. Experiments on ten bridge point clouds indicate that the method achieves an average modelling accuracy of C2Cതതതതത୅୳୲୭ 7.05 cm, and the average modelling time of 37.8 seconds. Compared to the laborious manual practice, this method can realize a direct time-savings of 95.8%.

Description

Keywords

Journal Title

Conference Name

International Symposium on Automation and Robotics in Construction

Journal ISSN

Volume Title

Publisher

Publisher DOI

Publisher URL

Relationships
Is supplemented by: