Modeling Ship Behavior based on Hidden Markov Models

Salma Zouaoui Elloumi, Jean-Paul Marmorat, Valérie Roy, and Nadia Maizi


Ship Behavior, Hidden Markov Models, Multiple Observation Sequence


Since 2001, works in the field of security have been considerably growing. All over the word, public places as markets, parkings, hotels, metro and train stations are permanently threatened by terroristic events. For this reason, researches are working every day to meet the need of security. In this article, we have been interested in securing harbors, equipments and people from any threatening event by studying, classifying and recognizing ships behaviors. We propose to use the probabilistic approach Hidden Markov Models (HMM) because of its promising performance in the field of behaviors learning and recognition. The idea is to gather the map of the port as well as ships trajectories in order to construct a set of models of all ships behaviors . Then, this set is exploited to classify every new ship trajectory moving in the harbor. Map of the harbor allowed the initialization of HMM models of ships behaviors, then the well-known Baum-Welch algorithm was chosen to learn models from ships trajectories obtained from port and finally the forward algorithm was used to classify and recognize every new ship behavior.

Important Links:

Go Back