Citation

Bhandari B, Park G. J. Transp. Saf. Secur. 2022; 14(4): 655-670.

Copyright

(Copyright © 2022, Southeastern Transportation Center, and Beijing Jiaotong University, Publisher Informa - Taylor and Francis Group)

DOI

10.1080/19439962.2020.1806423

PMID

unavailable

Abstract

The safety of railways, the nation's main transportation network, is currently drawing attention. This is mainly because of recent terrorist attacks aimed at private multipurpose facilities in a number of foreign countries. This article proposes a system for real-time monitoring of railway facilities and secure areas. Access control will be obtained using Raspberry Pi, an inexpensive micro-controller connected to the cloud via Amazon Web Service. Real-time surveillance is demonstrated by implementing computer vision and deep learning, and Twilio API. Intruders in restricted areas (such as tracks and electrical installations) can be detected with high precision and notifications can be sent to the safety and security managers in real time via short message service through cloud applications. The proposed system will assist the safety and security managers in responding swiftly and effectively to prevent or minimize risks that arise due to intruders.

Language: en

Keywords

computer vision; deep learning; intruder control; railway security; real-time monitoring