Enhance 3D point cloud accuracy through supervised machine learning for automated rolling stock maintenance: a railway sector case study

Randika K.W. Vithanage, Colin S. Harrison, Anjali K.M. DeSilva

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents findings of a case study conducted to introduce industrial robots into automatic train coupler inspection of Siemens Class 380 rolling-stock. The targets are localized by coalescing RGB and time of flight (ToF) sensor data. The study examines several supervised machine learning techniques to improve the overall accuracy of 3D point clouds. A cost factor which reflects root mean square, mean absolute error and coefficient of determination is defined to evaluate the performance of the learning algorithms. The best-suited models are further validated using simulation data and selected to include in overall robotic sensing system.
Original languageEnglish
Title of host publication2018 International Conference on Computing, Electronics & Communications Engineering (iCCECE)
EditorsMadhi H. Miraz, Peter S. Excell, Andrew Jones, Safeeullah Soomro, Maaruf Ali
PublisherIEEE
Pages242-246
Number of pages5
ISBN (Electronic)9781538649046
ISBN (Print)9781538649053
DOIs
Publication statusPublished - 7 Mar 2019

Keywords

  • sensor fusion, railway maintenance, robotic vision, supervised machine learning

Fingerprint Dive into the research topics of 'Enhance 3D point cloud accuracy through supervised machine learning for automated rolling stock maintenance: a railway sector case study'. Together they form a unique fingerprint.

  • Cite this

    Vithanage, R. K. W., Harrison, C. S., & DeSilva, A. K. M. (2019). Enhance 3D point cloud accuracy through supervised machine learning for automated rolling stock maintenance: a railway sector case study. In M. H. Miraz, P. S. Excell, A. Jones, S. Soomro, & M. Ali (Eds.), 2018 International Conference on Computing, Electronics & Communications Engineering (iCCECE) (pp. 242-246). IEEE. https://doi.org/10.1109/iCCECOME.2018.8658788