Maritime surveillance is an important research topic, considering that it is vital to keep the maritime environment safe against dangers like terroristic attacks and illegal activities such as out-of-region-fishery, human and drugs traffic. In a general maritime surveillance system, besides radar systems in large harbors, visual cameras are deployed along the shorelines which capture the videos of the maritime environment. As an important task for such a system, detected moving vessels’ behavior should be analyzed. To this end, it is essential to re-identify vessels while passing cameras in different locations.
The project focuses on research and development of innovative method for automatically re-identifying vessels in different locations. In order to analyze vessel behavior, we need to check its movements. Since vessels enter and exit into many surveillance camera’s field of view, a vessel re-identification method is required. However, as vessels pass cameras deployed on shorelines, their appearance differ, because cameras capture them from several viewpoints and sides.
Recently researchers have applied Convolutional Neural Networks (CNN) to pedestrian re-identification problem and achieved reasonable results. However, to our best knowledge, vessel re-identification problem is not investigated well yet. This opens an interesting research field in front of us to propose a CNN-based vessel re-identification method to later use in vessel behavior analysis.