Section-based object tracking

Abstract

Multiple-extremum issue including the well-known “singularity” problem is one of the major defects in kernel-based object tracking. This paper studies this important problem and presents a novel approach called section-based tracking (SBT) that is based on the section information provided by the division of the object's weight image. This approach serves to eliminate fake extremal points and make the tracking process more robust. Besides, this paper proposes qualitative rules for section-based kernel design, which help create a better kernel within SBT framework. Experiments show that both the SBT method and the kernel design rules conduce to better performance in tracking process.