Nowadays safety in railways is mostly achieved by automated system technologies such as ERTMS/ETCS. Nevertheless, on local railways (suburban and regional lines) several tasks still depend on the choices and actions of a human crew. With the aim to improve safety in such type of railways, this research proposes a system for the automatic detection and recognition of railway signs by means of the digital image processing technique. First field applications, carried out on the Italian railway network, show that the proposed system is very accurate (the percentage of correctly detected railway signs is about 97%), even at high train speeds.

AUTOMATED RAILWAY SIGNS DETECTION. PRELIMINARY RESULTS / Guerrieri, M; Parla, G. - In: TRANSPORT AND TELECOMMUNICATION. - ISSN 1407-6179. - ELETTRONICO. - 20:1(2019), pp. 12-21. [10.2478/ttj-2019-0002]

AUTOMATED RAILWAY SIGNS DETECTION. PRELIMINARY RESULTS

Guerrieri M;
2019-01-01

Abstract

Nowadays safety in railways is mostly achieved by automated system technologies such as ERTMS/ETCS. Nevertheless, on local railways (suburban and regional lines) several tasks still depend on the choices and actions of a human crew. With the aim to improve safety in such type of railways, this research proposes a system for the automatic detection and recognition of railway signs by means of the digital image processing technique. First field applications, carried out on the Italian railway network, show that the proposed system is very accurate (the percentage of correctly detected railway signs is about 97%), even at high train speeds.
2019
1
Guerrieri, M; Parla, G
AUTOMATED RAILWAY SIGNS DETECTION. PRELIMINARY RESULTS / Guerrieri, M; Parla, G. - In: TRANSPORT AND TELECOMMUNICATION. - ISSN 1407-6179. - ELETTRONICO. - 20:1(2019), pp. 12-21. [10.2478/ttj-2019-0002]
File in questo prodotto:
File Dimensione Formato  
Transport and Telecommunication Journal] Automated Railway Signs Detection. Preliminary Results.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 729.49 kB
Formato Adobe PDF
729.49 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/237718
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
  • OpenAlex ND
social impact