Abstract-The paper addresses how to efficiently exploit the Knowledge-Base (KB), e.g. environmental maps and characteristics of the targets, in order to gain improved performance in the tracking of multiple targets via measurements provided by a ship-borne radar operating in a littoral environment. In this scenario, the non homogeneity of the surveillance region makes the conventional tracking systems (not using the KB) very sensitive to false alarms and/or missed detections. It will be demonstrated that an effective use of the KB can be exploited at various levels of the tracking algorithms so as to significantly reduce the number of false alarms, missed detections, false tracks and improve true target track life. The KB will be exploited at two different levels. First, some key parameters of the tracking system are made dependent upon the track location, e.g., sea, land, coast, meteo zones (i.e. zones affected by meteorological phenomena) etc.. Secondly, modifications are introduced to cope with a priori identified regions with high clutter density (e.g. littoral areas, roads, meteo zones etc.). To evaluate the behavior of the proposed knowledge-based tracking systems, extensive results will be presented using both simulated and real radar data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.