A Gaussian Process Regression based Dynamical Models Learning Algorithm for Target Tracking

TL;DR

This paper introduces a Gaussian process regression-based method for learning target motion models that improve maneuvering target tracking accuracy without constant updates, outperforming traditional methods.

Contribution

It presents a novel data-driven approach using Gaussian process regression to learn shift-invariant target motion models applicable across different regions, integrated into particle filters.

Findings

Achieves around 90% performance improvement in multi-target tracking scenarios.

Effectively models natural shift-invariant motion without frequent updates.

Outperforms traditional IMM-PF methods in maneuvering scenarios.

Abstract

Maneuvering target tracking is a challenging problem for sensor systems because of the unpredictability of the targets' motions. This paper proposes a novel data-driven method for learning the dynamical motion model of a target. Non-parametric Gaussian process regression (GPR) is used to learn a target's naturally shift invariant motion (NSIM) behavior, which is translationally invariant and does not need to be constantly updated as the target moves. The learned Gaussian processes (GPs) can be applied to track targets within different surveillance regions from the surveillance region of the training data by being incorporated into the particle filter (PF) implementation. The performance of our proposed approach is evaluated over different maneuvering scenarios by being compared with commonly used interacting multiple model (IMM)-PF methods and provides around $90\%$ performance improvement for a multi-target tracking (MTT) highly maneuvering scenario.