Monocular visual odometry for underground railway scenarios

Mikel Etxeberria-Garcia*, Mikel Labayen, Fernando Eizaguirre, Maider Zamalloa, Nestor Arana-Arexolaleiba

*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

3 Citations (Scopus)

Abstract

In this paper, the application of monocular Visual Odometry (VO) solutions for underground train stopping operation are explored. In order to analyze if the application of monocular VO solutions in challenging environments as underground railway scenarios is viable, different VO architectures are selected. For that, the state of the art of deep learning based VO approaches is analyzed. Four categories can be defined in the VO approaches defined in the last few years: (1) supervised pure deep learning based solutions; (2) solutions combining geometric features and deep learning; (3) solutions combining inertial sensors and deep learning; and (4) unsupervised deep learning solutions. A dataset composed of underground train stop operations was also created, where the ground truth is labeled according to the onboard unit SIL-4 ERTMS/ETCS odometry data. The dataset was recorded by using a camera installed in front of the train. Preliminary experimental results demonstrate that deep learning based VO solutions are applicable in underground train stop operations.

Original languageEnglish
Title of host publicationFifteenth International Conference on Quality Control by Artificial Vision
EditorsKenji Terada, Akio Nakamura, Takashi Komuro, Tsuyoshi Shimizu
PublisherSPIE - International Society for Optical Engineering
Publication date2021
Article number1179402
ISBN (Electronic)9781510644267
DOIs
Publication statusPublished - 2021
Event15th International Conference on Quality Control by Artificial Vision - Tokushima, Virtual, Japan
Duration: 12 May 202114 May 2021

Conference

Conference15th International Conference on Quality Control by Artificial Vision
Country/TerritoryJapan
CityTokushima, Virtual
Period12/05/202114/05/2021
SponsorTechnical Committee on Industrial Application of Image Processing, Japan Society for Precision Engineering (JSPE)
SeriesProceedings of SPIE - The International Society for Optical Engineering
Volume11794
ISSN0277-786X

Bibliographical note

Funding Information:
This work was supported in part by the Basque Government through BIKAINTEK2018 program and CAF Signalling. In collaboration between Ikerlan, CAF Signalling and Mondragon Unibertsitatea.

Publisher Copyright:
© 2021 SPIE.

Keywords

  • Artificial intelligence
  • Autonomous train
  • Computer vision
  • Deep learning
  • Rail transportation

Fingerprint

Dive into the research topics of 'Monocular visual odometry for underground railway scenarios'. Together they form a unique fingerprint.

Cite this