Comparative study of ship detection techniques in TerraSAR-X images

Ship detection is nowadays quite an important issue in tasks related to sea traffic control, fishery management and ship search and rescue. Although it has traditionally been carried out by patrol ships or aircrafts, coverage and weather conditions can become a problem. Synthetic aperture radars can surpass these coverage limitations and work under any climatological condition. Three ship detectors are studied and compared in this paper. The Double Parameter Model, a CFAR technique with a three ring setup where sea clutter can be modeled in the outer ring, the SUMO detector, proposed by the Joint Research Centre and also based on CFAR techniques, and finally the Rice detector, that highlights the difference between dominant coherent scatterers such as ships and incoherent received signal in the Rice image domain. Four aspects will be taken into account in order to evaluate the performance of the detectors: detection rate, false alarm rate, ship characterization accuracy and processing time. While the Double Parameter Model attains good results in terms of both detection and false alarm rates, it is the Rice detector the one that stands out in every single category.