Particle filters for tracking closely spaced targets

Abstract

In this paper we will consider several algorithms for tracking closely spaced objects. In particular we will concentrate on various particle filter implementations. One particular problem when using a joint multi target particle filter is the so-called mixed labelling problem. This problem amounts to the fact that different particles will have a different labelling w.r.t. target identity. The combination of the mixed labelling problem and naïve or straightforward track extraction leads to performance degradation. This will be illustrated and alternative methods to alleviate this effect will be presented.