Automated Real-time Risk Assessment for Airport Passengers Using a Deep Learning Architecture

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 & 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.