Background modeling methods for visual detection of maritime targets

Abstract

We propose a system for real-time detection of maritime targets based on monocular video data. In the absence of a priori knowledge about their appearance, targets are detected implicitly via the statistical modeling of the scene's nonstationary background. A probabilistic treatment regarding target compactness is also presented. The proposed system currently acts as a stand-alone maritime surveillance application, and may also be used as an early detection stage within a larger maritime target tracking framework.