Scan-to-BIM for As-built Roads: Automatic Road Digital Twinning from Semantically Labeled Point Cloud Data

TL;DR

This paper introduces an automated scan-to-BIM framework for creating accurate geometric digital twins of roads from semantically labeled point cloud data, improving efficiency and precision in road asset modeling.

Contribution

It presents a novel pipeline that segments, extracts, and converts road assets into digital twins using a new data structure and algorithms, enhancing automation and accuracy.

Findings

Achieves an average distance error of 1.46 cm.

Processes 6.29 meters of road per second.

Validated on six real-world road segments totaling 1,200 meters.

Abstract

Creating geometric digital twins (gDT) for as-built roads still faces many challenges, such as low automation level and accuracy, limited asset types and shapes, and reliance on engineering experience. A novel scan-to-building information modeling (scan-to-BIM) framework is proposed for automatic road gDT creation based on semantically labeled point cloud data (PCD), which considers six asset types: Road Surface, Road Side (Slope), Road Lane (Marking), Road Sign, Road Light, and Guardrail. The framework first segments the semantic PCD into spatially independent instances or parts, then extracts the sectional polygon contours as their representative geometric information, stored in JavaScript Object Notation (JSON) files using a new data structure. Primitive gDTs are finally created from JSON files using corresponding conversion algorithms. The proposed method achieves an average distance error of 1.46 centimeters and a processing speed of 6.29 meters per second on six real-world road segments with a total length of 1,200 meters.