Share Email Print
cover

Proceedings Paper

Automated real-time risk assessment for airport passengers using a deep learning architecture
Author(s): Stelios C. A. Thomopoulos; Stelios Daveas; Antonios Danelakis
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Airport control check points are required to operate and maintain modern security systems preventing malicious actions. This paper presents a methodology, introduced in the context of the FLYSEC project [30], that provides real-time risk assessment for airport passengers based on their trajectories. The proposed methodology implements a deep learning architecture. It is fully automated, reducing the workload of the video surveillance operators making leading to less error-prone conclusions. It has been integrated with the Command and Control System (C2) of iCrowd, a crowd simulation platform developed by the Integrated Systems Lab of the Institute of Informatics and Telecommunications in NCSR Demokritos. iCrowd features a highly-configurable, high-fidelity agent-based behavior simulator and provides a realistic environment that enables behaviors of simulated actors (e.g. passengers, personnel, malicious actors), instantiates the functionality of hardware security technologies, and simulates passengers’ facilitation and customer service. iCrowd has been used for conducting experiments on simulated scenarios in order to evaluate the proposed risk assessment scheme. The experimental results indicate that the proposed risk assessment scheme is very promising and can reliably be used in an airport security frame for evaluating and/or enveloping security tracking systems performance.

Paper Details

Date Published: 7 May 2019
PDF: 12 pages
Proc. SPIE 11018, Signal Processing, Sensor/Information Fusion, and Target Recognition XXVIII, 110180O (7 May 2019); doi: 10.1117/12.2519857
Show Author Affiliations
Stelios C. A. Thomopoulos, National Ctr. for Scientific Research Demokritos (Greece)
Stelios Daveas, National Ctr. for Scientific Research Demokritos (Greece)
Antonios Danelakis, National Ctr. for Scientific Research Demokritos (Greece)


Published in SPIE Proceedings Vol. 11018:
Signal Processing, Sensor/Information Fusion, and Target Recognition XXVIII
Ivan Kadar; Erik P. Blasch; Lynne L. Grewe, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray