University of Twente Student Theses

Login

3D point cloud segmentation and automation for railway catenary arches

Bozov, P. (2022) 3D point cloud segmentation and automation for railway catenary arches.

[img] PDF
1MB
Abstract:Point Clouds are increasingly utilised for purposes requiring object modelling and the creation of a 3D representation. Using LiDar sensors, the Dutch company "Strukton" is scanning railroad rails in order to simplify their inspection process with the aim to move to digitalization. A previous research was able to create a data pipeline that accepts a point cloud as input and produces a 3D CAD model as output. Using this already-implemented data pipeline, this project aims to optimise its procedures, rework it so that it may be utilised for the whole catenary arches of railways, and ultimately automate it completely. The pipeline works with two main processes - segmentation and object retrieval. This research focuses on modifying the RANSAC sampling and fine alignment processes from [21] and explores techniques for CAD placement to achieve a fully automated data pipeline.
Item Type:Essay (Bachelor)
Clients:
Saxion University of Applied Sciences
Strukton Rail
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:https://purl.utwente.nl/essays/91791
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page