Deep Multitask Learning for Railway Track Inspection

Abstract

Railroad tracks need to be periodically inspected and monitored to ensure safe transportation. Automated track inspection using computer vision and pattern recognition methods has recently shown the potential to improve safety by allowing for more frequent inspections while reducing human errors. Achieving full automation is still very challenging due to… (More)
DOI: 10.1109/TITS.2016.2568758

Topics

17 Figures and Tables

Cite this paper

@article{Gibert2017DeepML, title={Deep Multitask Learning for Railway Track Inspection}, author={Xavier Gibert and Vishal M. Patel and Rama Chellappa}, journal={IEEE Transactions on Intelligent Transportation Systems}, year={2017}, volume={18}, pages={153-164} }