Semi-Automated As-Built Modeling of Light Rail System Guide Beams - Robotics Institute Carnegie Mellon University

Semi-Automated As-Built Modeling of Light Rail System Guide Beams

Pingbo Tang, Burcu Akinci, and Daniel Huber
Conference Paper, Proceedings of ASCE Construction Research Congress, May, 2010

Abstract

For a light rail system, smooth contact between the vehicle and the guide beam is critical for reducing the friction and the vibration of an operating vehicle. Therefore, the shape of guide beams needs to be controlled with mm-level accuracy during the construction. Currently, most methods for detecting shape defects of guide beams, such as experimental run of vehicles, are costly and tedious. In addition, these methods can only identify defects after the completion of the construction, and cause reworks and delays of defects fixings. From dense point clouds collected by laser scanners, inspectors can manually extract geometric features and conduct virtual inspections of guide beams. However, the manual geometric feature extraction process impedes effective utilization of point clouds for the shape analysis of guide beams. Aiming at improving the efficiency of utilizing laser scanning technology for guide beam quality control, this research developed a semi-automatic approach for simultaneously extracting the axis parameters (e.g., radius) and cross-section features (e.g., width) of a guide beam using a Hough-Transform based approach, and discusses factors (e.g., data density) influencing the performance of this approach.

BibTeX

@conference{Tang-2010-10432,
author = {Pingbo Tang and Burcu Akinci and Daniel Huber},
title = {Semi-Automated As-Built Modeling of Light Rail System Guide Beams},
booktitle = {Proceedings of ASCE Construction Research Congress},
year = {2010},
month = {May},
keywords = {Laser Scanning, Geometric Feature Extraction, Information Retrieval, Quality Control, Surveying, 3D Modeling},
}