The main scope of this Master thesis is to analyze and design an innovative technological solution for Complex Event Recognition for Maritime Surveillance purposes, based entirely on the approach presented in the Paper “Event Recognition for Maritime Surveillance” by Kostas Patroumpas, Alexander Artikis, Nikos Katzouris, Marios Vodas, Yannis Theodoridis and Nikos Pelekis in the context of the AMINESS project. The master Thesis aims to tackle the challenge of processing and analyzing the available AIS Data sets in real time using Apache Flink. Apache Flink is a real time high-performance and accurate natural Stream Processing Engine from Apache Software Foundation. The ultimate goal is to inspire Maritime authorities to develop their digital culture and empower their ICT departments with a new big data innovative tool that uses the existing Paper’s algorithms and semantics in an intelligent way, so as to detect vessel’s Trajectories in the Aegean Sea while performing accurate Complex Event Recognition. The technical approach and the effective reasoning of complex events is totally based on the business logic of RTEC and the Event Calculus formal language semantics. We are going to map these semantics into Apache Flink DataStream and Dataset API and create an efficient alternative technical approach.