Learning to track on-the-fly using a particle filter with annealed- weighted QPSO modeled after a singular Dirac delta potential

TL;DR

This paper introduces an advanced particle filter for visual tracking that combines memory-guided proposal updates with an annealed quantum-behaved PSO resampling scheme, effectively reducing sample impoverishment.

Contribution

It presents a novel evolutionary particle filter integrating memory-guided proposals and an annealed QPSO resampling, improving tracking accuracy and robustness.

Findings

Outperforms traditional particle filters on benchmark sequences.

Reduces sample impoverishment in particle filtering.

Enhances tracking robustness with annealed QPSO resampling.

Abstract

This paper proposes an evolutionary Particle Filter with a memory guided proposal step size update and an improved, fully-connected Quantum-behaved Particle Swarm Optimization (QPSO) resampling scheme for visual tracking applications. The proposal update step uses importance weights proportional to velocities encountered in recent memory to limit the swarm movement within probable regions of interest. The QPSO resampling scheme uses a fitness weighted mean best update to bias the swarm towards the fittest section of particles while also employing a simulated annealing operator to avoid subpar fine tune during latter course of iterations. By moving particles closer to high likelihood landscapes of the posterior distribution using such constructs, the sample impoverishment problem that plagues the Particle Filter is mitigated to a great extent. Experimental results using benchmark sequences imply that the proposed method outperforms competitive candidate trackers such as the Particle Filter and the traditional Particle Swarm Optimization based Particle Filter on a suite of tracker performance indices.