Tracking spawning objects

Abstract

Many multi-object tracking scenarios are complicated by the fact that an object of interest may spawn additional objects which, for some period of time, follow roughly the same trajectory as the original object and then fall away. The challenge is then to discriminate the original object from the spawned ancillaries in a timely fashion. This study proposes a solution to this problem based on the increasingly well-known multi-object track-before-detect algorithm called the cardinalised probability hypothesis density (CPHD) filter. Precisely, the authors assume zero false alarms (ZFA) in the CPHD filter, and apply the proposed scheme to linear and non-linear simulation scenarios based on widely used object-trajectory and sensor models. The authors have also demonstrated that a Gaussian mixture implementation of the ZFA-CPHD filter (i) establishes stable estimates of object number, (ii) rapidly eliminates the ancillary objects and (iii) detects and accurately estimates the trajectory of the original object of interest.

Conditional path sampling for stochastic differential equations through drift relaxation

“…We use drift relaxation to produce samples from the density (12). The Markov chain at each level of the drift relaxation algorithm is constructed using Hybrid Monte Carlo (HMC) [10].…”

“…In this context, the accurate tracking of each target becomes crucial. Suppose that only one of the targets is of interest and the rest act as decoys [12]. The inability to track each potential target accurately can lead to ambiguity about the targets' movement if the observations for different targets are close.…”

Unscented particle implementation of cardinality balanced multi-target multi-Bernoulli filter

“…The parameters of dynamic system is given by Firstly, let us consider a relatively simple scenario of zero false alarm (ZFA) situation inspired by Mahler and Maroulas in [12]. The true trajectories of four targets in a single trail are showed in Fig.1.…”