Semantic Segmentation of Terrestrial Laser Scans of Railway Catenary Arches: A Use Case Perspective

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.

Point Cloud Analysis of Railway Infrastructure: A Systematic Literature Review

“…We again emphasise developing a benchmark dataset set comparable to the KITTI dataset available for self-driving cars. The dataset published by Ton [92] is a positive step in this direction. We propose creation of a public benchmark dataset as a joint collaborative effort.…”

“…One interesting finding of our literature review is the lack of public benchmark datasets consisting of point clouds in the context of railway infrastructure. However, we have recently published a fully labelled dataset consisting of catenary arches [20], which is the only openly available dataset to the best of our knowledge. Although a few datasets are mentioned in the literature, they are not openly accessible.…”

“…A challenge for railway scenes is the large variance in object sizes (a top bar can be well over 20 metres long, while an insulator typically is around 30 centimetres [20], which is a size ratio of at least 60 times). An additional This article has been accepted for publication in IEEE Access.…”

Digital Twin for Railway: A Comprehensive Survey

“…• Point Cloud scanning: is a 3D scanning technique used to capture the shape and position of objects by collecting large sets of data points named Point Cloud Data (PCD). The PCD can be applied to generate railway masts [82], catenary arches [83], or the Overhead Line Equipment (OLE) elements [24]. This technique provides an efficient approach to developing infrastructure models for DTRs.…”

“…They also presented a four-stage methodology for developing edge-based AI solutions, which includes AI models selected based on multi-objective problems and implemented using XAI strategies taking the diagnostic of stagger amplitude as a use case. The study in [83] utilized terrestrial laser scanning and semantic segmentation techniques to generate accurate DTs for upkeeping, surveillance, and planning. A case study involving railway catenary arches was considered and a modified PointNet++ model was implemented.…”