Machine Learning-Assisted Man Overboard Detection Using Radars

Abstract

One of the most crucial emergencies that require instant action to be taken during traveling across water is the so-called man overboard (MOB). Thus, constant monitoring equipment needs to be installed for the fast notice and detection of the victim to be rescued, if an incident happens. Despite the fact that different installations such as radar sensors, thermal cameras etc., can be handy, a combination of these could be beneficial yet it would increase the complexity. Nevertheless, the full potential may be not reached yet. The key component to what needs to be done in order to achieve the utmost accuracy is artificial intelligence (AI). That is, with the aid of AI, one can deploy an automated surveillance system capable of making its own humanlike decisions regarding such incidents like MOB. To achieve this, fully organized real-time cooperation among the concerned system components is essential. The latter holds since in such dynamically changing operational environments like these, information must be distributed fast, errorless and reliably to the decision center. This study aims to analyze and demonstrate the outcome of an integrated sensor-based system that utilizes AI, implemented for ship incidents. Different machine learning algorithms were used where each one of them made use of information that originated from a cluster of radar sensors located remotely. In particular, the deployed system’s objective is to detect human motion so it can be used to protect against potentially fateful events during ship voyages.