SAR Ship Detection and Self-Reporting Data Fusion Based on Traffic Knowledge

Abstract

The improvement in Maritime Situational Awareness, the capability of understanding events, circumstances, and activities within and impacting the maritime environment, is nowadays of paramount importance for safety and security. The integration of spaceborne synthetic aperture radar (SAR) data and automatic identification system (AIS) information has the appealing potential to provide a better picture of what is happening at sea by detecting vessels that are not reporting their positioning data or, on the other side, by validating ships detected in satellite imagery. In this letter, we propose a novel architecture that is able to increase the quality of SAR/AIS fusion by exploiting knowledge of historical vessel positioning information. Experimental results are presented, testing the algorithm in the specific area of Dover Strait using real SAR and AIS data.Index Terms-Automatic identification system (AIS), data fusion, Maritime Situational Awareness (MSA), ship detection, synthetic aperture radar (SAR).

Analysis of Ship Detection Performance with Full-, Compact- and Dual-Polarimetric SAR

“…However, with the higher resolution of the SAR image, the sea clutter becomes complex in the time and spatial domains, and then the existing models are not suitable, resulting in the severe degradation of the CFAR detection performance and many false alarms [4]. Additionally, the parameter estimation is complex, and the threshold cannot be acquired easily [5].To overcome the drawbacks of the CFAR method, ship detection methods based on new features have been studied by researchers, and many results has been achieved [6][7][8]. For example, based on Cloude decomposition, Wang et al [9] used the local uniformity of the third eigenvalue of a polarization coherence matrix (T) to detect ships.…”

“…To overcome the drawbacks of the CFAR method, ship detection methods based on new features have been studied by researchers, and many results has been achieved [6][7][8]. For example, based on Cloude decomposition, Wang et al [9] used the local uniformity of the third eigenvalue of a polarization coherence matrix (T) to detect ships.…”

Integration of Automatic Identification System (AIS) Data and Single-Channel Synthetic Aperture Radar (SAR) Images by SAR-Based Ship Velocity Estimation for Maritime Situational Awareness

“…The azimuth offset makes AIS-SAR data matching difficult and it must be compensated for, especially in highly congested areas. The common approach for AIS-SAR data matching [17][18][19]31,32] is shown in Figure 2. Positions of vessels in AIS data, interpolated at SAR image epoch, are referred to as AIS-based ship geographic coordinates.…”

Generic framework for vessel detection and tracking based on distributed marine radar image data

“…Thus, the refinement of the situation picture is the motivation for many works applying methods of multisensor, multi-target tracking. In [16] and [30] AIS data are fused with Synthetic Aperture Radar (SAR) imagery and/ or coastal radar to provide a reliable and precise situation picture for large-scale maritime surveillance. In the same context different authors, such as [7,29] and [31], have also studied the benefits of fusing multiple coastal Over-the-Horizon (OTH) radars in terms of an improved MTT performance and increased area of coverage.…”