IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 1 Knowledge-Based Multi-Target Ship Tracking for HF Surface Wave Radar Systems Gemine Vivone, Paolo Braca, Member, IEEE, and Jochen Horstmann Abstract—These last decades spawned a great interest towards low-power High-Frequency (HF) Surface-Wave (SW) radars for ocean remote sensing. By virtue of their over-the-horizon coverage capability and continuous-time mode of operation, these sensors are also effective long-range early-warning tools in maritime situational awareness applications providing an additional source of information for target detection and tracking. Unfortunately, they also exhibit many shortcomings that need to be taken into account, and proper algorithms need to be exploited to overcome their limitations. In this paper, we develop a Knowledge-Based (KB) multi- target tracking methodology, that takes advantage of a priori information on the ship traffic. This a priori information is given by the ship sea lanes and by their related motion models, which together constitute the basic building blocks of a Variable Structure Interactive Multiple Model (VS-IMM) procedure. False alarms and missed detections are dealt with using a Joint Probabilistic Data Association (JPDA) rule and non-linearities are handled by the means of the Unscented Kalman Filter (UKF). The KB-tracking procedure is validated using real data ac- quired during an HF-radar experiment in the Ligurian Sea (Mediterranean Sea). Two HFSW radar systems were operated to develop and test target detection and tracking algorithms. The overall performance is defined in terms of time-on-target, false alarm rate, track fragmentation, and accuracy. A full statistical characterization is provided using one month of data. A significant improvement of the KB-tracking procedure, in terms of system performance, is demonstrated in comparison with the standard approach recently presented in [1]. The main improvement of our approach is the better capability of following targets without increasing the false alarm rate. This increment is much more evident in the region of low false alarm rate where it can be over the 30% for both the HFSW radar systems. The KB-tracking exhibits on average a reduction of the track fragmentation of about the 20% and the 13% of the utilized HFSW-radar systems. Index Terms—High-frequency surface-wave radar, target de- tection, target tracking, knowledge-based tracking, maritime surveillance. I. I NTRODUCTION T HE oceans connect nations globally through an inter- dependent network of economic, financial, social and political relationships. The statistics are compelling: 70% of the Earth is covered in water; 80% of the world’s population lives within 100 miles of the coast; 90% of the world’s G. Vivone and P. Braca are with the North Atlantic Treaty Organi- zation (NATO) Science and Technology Organization (STO) Centre for Maritime Research and Experimentation, 19126 La Spezia, Italy (e-mails: {gemine.vivone,paolo.braca}@cmre.nato.int). J. Horstmann is with Helmholtz-Zentrum Geesthacht, 21502 Geesthacht, Germany (e-mail: jochen.horstmann@hzg.de). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier commerce is seaborne and 75% of that trade passes through a few, vulnerable, canals and international straits. The maritime environment includes trade routes, choke points, ports, and other infrastructure such as pipelines, oil and natural gas platforms and trans-oceanic telecommunications cables [2]. Consequently, the maritime security environment is one of the most important operative scenarios, and surveillance ac- tivities are the crux of these activities. Ship traffic monitoring represents one of the biggest challenges (e.g. in terms of law enforcement, search and rescue, environmental protection and resource management) and, in the last years, it has led to intensive research activities in order to exploit existing sensor systems in support of maritime surveillance. In this domain several monitoring assets can be exploited, from ground-based radar technologies to satellite sensors. However, it is important to take into consideration that many of these traditional solutions suffer from physical limitations, and only a smart integration of these different and often com- plementary systems can guarantee satisfactory performance. For instance, standard microwave radars operate only within line-of-sight propagation, with a maximum range of some dozens of kilometers, and satellite sensors (e.g. synthetic aperture radars) cannot grant a continuous temporal coverage of the region of interest with an adequate level of real-time surveillance. High-Frequency (HF) Surface-Wave (SW) radar systems have been proposed as a cost-effective tool able to overcome many of these limitations. They can provide additional in- formation on the vessel traffic, by virtue of their capability of detecting targets over-the-horizon, their continuous-time coverage and their ability to estimate ship velocity through the Doppler data [3]. HFSW radars work in the 3 - 30 MHz band, with wavelengths between 100 m and 10 m, respec- tively. In this range, vertically polarized radio waves have the ability to propagate as surface waves. Low-power HFSW radar systems have been mainly developed for ocean remote sensing applications, e.g. surface currents and sea state mapping, wind extraction, wave spectra analysis and, recently, tsunami early- warning detection [4]. Few commercial systems based on the HFSW concept are available. They can be classified into two families [7]. The first one consists of high power systems of very large size and extension. An example is the SWR-503 HFSW radar commer- cialized by Raytheon, which has a receiving antenna composed by a linear array of 16 monopole and 7-element log-periodic monopole for transmission, with an average transmitting power of 1.6 kW [5], see also Tab. I. The second family is repre- sented by systems that are typically used for environmental monitoring purposes. The most common used systems are