Abstract
Some railway solutions are the results of technology push. The development of low cost computers and cameras makes it possible to automate detection tasks in different industry domains. In this article, we develop the blocking points that arise for the adoption of A.I. technologies for functions involving safety. We remind the useful elements for a safety demonstration, and for the definition of tests or simulations which bring complements to this validation. We propose a paradigm shift for the demonstration of safety, in a framework where a formal demonstration is no longer possible, with two methods “proven in use” and NABS (not absolute but sufficient).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Principe «GAME» (Globalement Au Moins Équivalent)-STRMTG – version 2
Temel, D., Chen, M.H.: Traffic sign detection under challenging conditions: a deeper look into performance variations and spectral characteristics. IEEE Trans. Intell. Transp. Syst., 1–11 (2019)
Marmo, R., Lombardi, L.: Railway sign detection and classification. In: IEEE Intelligent Transportation Systems Conference, pp. 1358–1363 (2006)
Birch, J., et al.: Safety cases and their role in ISO 26262 functional safety assessment. In: Bitsch, F., Guiochet, J., Kaâniche, M. (eds.) SAFECOMP 2013. LNCS, vol. 8153, pp. 154–165. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40793-2_15
Li, G., Hamilton, W.I.: Driver detection and recognition of lineside signals and signs at different approach speeds. Cogn. Technol. Work 8, 30–40 (2006)
Ingibergsson, J.T.: Explicit image quality detection rules for functional safety in computer vision. In: VISIGRAPP (6: VISAPP), pp. 433–444 (2017)
NF EN 50128: Railways application – Communication, signaling and processing systems – Software for railway control and protection systems, 01 October 2011
NF EN 50129 (E) Prépubliée/Prepublished (2018-11-23) - Railways application – Communication, signaling and processing systems – Safety related electronic systems for signaling
NF EN 50126: Railway Applications - The Specification and demonstration of reliability, availability, maintainability and safety (RAMS) - Part 1: generic RAMS process, Part 2: Systems Approach to Safety
Kalra, N., Paddock, S.M.: How many miles of driving would it take to demonsytrate autonomous vehicle reliability? Transp. Res. Part Policy Pract. 94, 182–193 (2016)
“proposed cross acceptance for railways signaling systems and equipment” Committee report N°6 – IRSE – Institution of Railways Signal Engineers
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Boulineau, J.F. (2020). Safe Recognition A.I. of a Railway Signal by On-Board Camera. In: Bernardi, S., et al. Dependable Computing - EDCC 2020 Workshops. EDCC 2020. Communications in Computer and Information Science, vol 1279. Springer, Cham. https://doi.org/10.1007/978-3-030-58462-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-58462-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58461-0
Online ISBN: 978-3-030-58462-7
eBook Packages: Computer ScienceComputer Science (R0)