Ship recognition and classification in electro-optical satellite imagery is a challenging problem with important military applications. The problem is similar to that of face recognition, but with many unique considerations. A ship's appearance can vary dramatically from image to image depending on factors such as lighting condition, sensor angle, and ocean state, and there is often wide variation between ships of the same class. Collecting and labeling sufficient training data is another challenge. We consider how appropriate feature selection and description can assist in addressing these challenges. Our proposed algorithm for vessel classification combines shape invariant features such as SIFT with a well known face recognition algorithm from the theory of sparse representation and compressive sensing. We demonstrate improved classification accuracy using invariant features at significant key points instead of random features to represent images. We also discuss how algorithms such as this are currently implemented to detect and classify ships and other objects in ocean imagery.
Detection of vessels from space-based synthetic aperture radar (SAR) data is an important area of research with many applications, including fisheries monitoring, counter-piracy, and maritime border security. The detection of vessels on the ocean surface in SAR imagery requires that the vessel has sufficiently high radar cross section (RCS). In general, the RCS of an object is a function of the object's material, size, and shape, as well as RADAR parameters such as center frequency. Even, two objects of the same size may have different RCSs based on construction materials (i.e., wood versus metal). In Ghana, as in much of the Gulf of Guinea, wooden canoes 6-25 m in length represent a significant percentage of maritime traffic. These canoes are not easy to detect and track in coastal RADAR, nor are they easily detected in SAR imagery. These vessels may represent a significant risk to maritime safety and security. Here, we describe one possible solution for the problem described-above based on inexpensive, versatile corner reflectors with high RCS. Specifically, we describe the design and construction of high RCS corner reflectors and results from a series of experiments in which corner reflectors were installed on wooden canoes. During the experiments, canoes were deployed to specific locations off the coast of Ghana at specific times, corresponding to the acquisition of space-based SAR imagery. We present results from these experiments, which indicate that wooden canoes with these corner reflectors can be detected in space-based SAR imagery.Index Terms-Maritime domain awareness, small vessel detection, synthetic aperture radar (SAR).
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.