Semantic Segmentation of Terrestrial Laser Scans of Railway Catenary Arches: A Use Case Perspective
Open Access
Abstract
Having access to accurate and recent digital twins of infrastructure assets benefits the renovation, maintenance, condition monitoring, and construction planning of infrastructural projects. There are many cases where such a digital twin does not yet exist, such as for legacy structures. In order to create such a digital twin, a mobile laser scanner can be used to capture the geometric representation of the structure. With the aid of semantic segmentation, the scene can be decomposed into different object classes. This decomposition can then be used to retrieve cad models from a cad library to create an accurate digital twin. This study explores three deep-learning-based models for semantic segmentation of point clouds in a practical real-world setting: PointNet++, SuperPoint Graph, and Point Transformer. This study focuses on the use case of catenary arches of the Dutch railway system in collaboration with Strukton Rail, a major contractor for rail projects. A challenging, varied, high-resolution, and annotated dataset for evaluating point cloud segmentation models in railway settings is presented. The dataset contains 14 individually labelled classes and is the first of its kind to be made publicly available. A modified PointNet++ model achieved the best mean class Intersection over Union (IoU) of 71% for the semantic segmentation task on this new, diverse, and challenging dataset.Keywords
Funding Information
- TechForFuture
- University of Twente
This publication has 43 references indexed in Scilit:
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- Automated Recognition of Railroad Infrastructure in Rural Areas from LIDAR DataRemote Sensing, 2015
- The Use of Airborne and Mobile Laser Scanning for Modeling Railway Environments in 3DRemote Sensing, 2014
- Close-Range Photogrammetry with Laser Scan Point CloudsSAE International Journal of Advances and Current Practices in Mobility, 2012
- Automatic reconstruction of as-built building information models from laser-scanned point clouds: A review of related techniquesAutomation in Construction, 2010
- A progressive morphological filter for removing nonground measurements from airborne LIDAR dataIEEE Transactions on Geoscience and Remote Sensing, 2003
- A comparison between photogrammetry and laser scanningISPRS Journal of Photogrammetry and Remote Sensing, 1999
- The quickhull algorithm for convex hullsACM Transactions on Mathematical Software, 1996
- Multidimensional binary search trees used for associative searchingCommunications of the ACM, 1975