Vision-based maritime surveillance system using fused visual attention maps and online adaptable tracker

Abstract

This paper presents a vision-based system for maritime surveillance using moving PTZ cameras. This system is intended to be used as an early warning system by local authorities. It fuses a visual attention method that exploits low-level image features appropriately selected for maritime environment, with an online adaptable neural network tracker, without making any assumptions about environmental or visual conditions. Systems performance was evaluated with videos from cameras placed at Limassol port and Venetian port of Chania and concerns robustness compared to dynamically changing visual conditions and different kinds of vessels, all in real time.