Automatic surveillance systems for the maritime domain are becoming more and more important due to a constant increase of naval traffic and to the simultaneous reduction of crews on decks. However, available technology still provides only a limited support to this kind of applications. In this paper, a modular system for intelligent maritime surveillance, capable of fusing information from heterogeneous sources, is described. The system is designed to enhance the functions of the existing Vessel Traffic Services systems and to be deployable in populated areas, where radar-based systems cannot be used due to the high electromagnetic radiation emissions. A quantitative evaluation of the proposed approach has been carried out on a large and publicly available data set of images and videos, collected from multiple real sites, with different light, weather, and traffic conditions.

The constant increase in marine traffic and the simultaneous growth of the demand for exploiting marine areas (e.g., installing offshore wind power plants) require an adequate planning strategy for managing high traffic volumes. Maritime Spatial Planning (MSP) is the process of public development of an allocation plan for distributing, both spatially and temporally, human activities in marine areas. The adoption of e-Navigation is a possible solution for improving safety and security at sea by integrating maritime information on board and ashore. Automatic Identification System (AIS) data represents a fundamental source of information, since the analysis of AIS data can highlight the presence of congested areas as well as of illegal actions, such as smuggling, pollution, and unauthorized phishing in protected areas. Indeed, those activities are often characterized by abnormal manoeuvres that can be recognized by analyzing the routes of the vessels. However, the huge dimension of the AIS data to process requires the adoption of careful strategies for the data visualization. In this paper, we present a complete pipeline for visualizing ship routes from raw AIS data, which is a fundamental pre-requisite for carrying out a significant AIS-based route analysis, and describe a real case study, where 90 million AIS records, corresponding to one month of world-wide observations, are visualized using only open-source software

No abstract

No abstract

Surveillance systems for the maritime domain are becoming more and more important. However, available technology still provides only a limited support to this kind of applications. In this book chapter, we describe a framework for intelligent surveillance in the maritime domain, designed for fusing information from heterogeneous sources. Electro-optical cameras are used as main sensors, in order to enhance the functionalities of current Vessel Traffic Services (VTS) systems. Furthermore, the framework can be used for the detection of non-cooperative targets and can be deployed in populated areas, where radar-based systems cannot be used due to electromagnetic radiation emissions. A quantitative evaluation of the proposed approach has been carried out on a large dataset of images and videos, collected from di different real sites. Such data are publicly available from the MarDCT -Maritime Detection , Classification and Tracking dataset.