Adaptive mixture approximation for target tracking in clutter

TL;DR

This paper investigates how adaptive mixture model reduction can improve computational efficiency and tracking accuracy in cluttered target tracking scenarios, balancing hypothesis management and performance.

Contribution

It introduces an analysis of adaptive mixture reduction applied to Bayesian target tracking with clutter, highlighting its effectiveness in managing hypotheses and computational resources.

Findings

Adaptive mixture reduction improves tracking efficiency.

The method maintains accuracy with fewer hypotheses.

Computational resources are optimized without sacrificing performance.

Abstract

Target tracking represents a state estimation problem recurrent in many practical scenarios like air traffic control, autonomous vehicles, marine radar surveillance and so on. In a Bayesian perspective, when phenomena like clutter are present, the vast majority of the existing tracking algorithms have to deal with association hypotheses which can grow in the number over time; in that case, the posterior state distribution can become computationally intractable and approximations have to be introduced. In this work, the impact of the number of hypotheses and corresponding reductions is investigated both in terms of employed computational resources and tracking performances. For this purpose, a recently developed adaptive mixture model reduction algorithm is considered in order to assess its performances when applied to the problem of single object tracking in the presence of clutter and to provide additional insights on the addressed problem.