Visual region-based tracking is a heavily researched general approach to following a target across a temporal image sequence. Little research, however, has addressed the interelationships of the various approaches at a theoretical level. In response to this situation, the present report describes a unifyting framework for a wide range of region trackers in terms of the amount of spatial layout that they maintain in the target representation. This framework yields a general notaion from which any of these trackers can be instantiated. To illustrate the pratical utility of the framework, a range of region trackers are instantiated within its formalism and used to document empirically the impact of maintaining variable amounts of spatial information during target tracking.

Download paper in PDF format.

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.