Frame-rate omnidirectional surveillance and tracking of camouflaged and occluded targets

Abstract

Video surveillance involves watching an area for significant events. Perimeter security generally requires watching areas that afford trespassers reasonable cover and concealment. By definition, such "interesting" areas have limited visibility. Furthermore, targets of interest generally attempt to conceal themselves within the cover sometimes adding camouflage to further reduce their visibility. Such targets are only visible "while in motion". The combined result of limited visibility distance and target visibility severely reduces the usefulness of any panning-based approach. As a result, these situations call for a wide field of view, and are a natural application for omni-directional VSAM (video surveillance and monitoring). This paper describes an omni-directional tracking system. After motivating its use, we discuss some domain application constraints and background on the paracamera. We then go through the basic components of the frame-rate Lehigh Omni-directional Tracking System (LOTS) and describe some of its unique features. In particular, the system's combined performance depends on novel adaptive multi-background modeling and a novel quasi-connected-components technique. These key components are described in some detail, while other components are summarized. We end with a summary of an external evaluation of the system.