Answers are grounded in this paper and cite their sources.
Generating geometric digital twins (GDTs) of railway overhead line equipment (OLE) from point cloud data (PCD) using manual or semi-automated approaches is labour-intensive. This diminishes their practical benefits, with 74% of modelling effort spent converting PCD into GDTs. Automation reduces cost and effort, yet state-of-the-art methods struggle to deliver kilometre-scale GDTs without precision loss or manual intervention. This paper presents an automated method combining topology-aware segmentation, rule-based classification, and template-driven geometric reconstruction. Leveraging engineering rules and OLE spatial relationships, it enables modelling in cluttered, partially occluded scenes. OLE elements are segmented into labelled clusters, then aligned with parametric assemblies to generate industry foundation classes (IFC) models. Evaluation on 18.5 km of PCD achieved F1 scores of 98.3% for C sections, 89.8% for contact and 84.1% for catenary cables, with ±5.6 cm RMSE. Automation saved 98.6% of time versus manual workflows. This contributes a topology-informed strategy for scalable digital twin generation.
No takes yet. Share an insight, caveat, or question.
Ariyachandra et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: