Integrated Gaussian Processes for Robust and Adaptive Multi-Object Tracking

TL;DR

This paper introduces robust, adaptive multi-object tracking methods using integrated Gaussian processes and Poisson models, capable of online learning, class inference, and track stitching, outperforming existing algorithms in challenging environments.

Contribution

The paper develops two novel trackers, GaPP-Class and GaPP-ReaCtion, that integrate Gaussian processes and Poisson models with particle filtering for improved robustness and adaptability in multi-object tracking.

Findings

GaPP-ReaCtion reduces track breaks by around 30% in radar data.

The proposed methods outperform state-of-the-art algorithms in synthetic and real data.

Effective online hyperparameter learning and object classification are achieved.

Abstract

This paper presents a computationally efficient multi-object tracking approach that can minimise track breaks (e.g., in challenging environments and against agile targets), learn the measurement model parameters on-line (e.g., in dynamically changing scenes) and infer the class of the tracked objects, if joint tracking and kinematic behaviour classification is sought. It capitalises on the flexibilities offered by the integrated Gaussian process as a motion model and the convenient statistical properties of non-homogeneous Poisson processes as a suitable observation model. This can be combined with the proposed effective track revival / stitching mechanism. We accordingly introduce the two robust and adaptive trackers, Gaussian and Poisson Process with Classification (GaPP-Class) and GaPP with Revival and Classification (GaPP-ReaCtion). They employ an appropriate particle filtering inference scheme that efficiently integrates track management and hyperparameter learning (including the object class, if relevant). GaPP-ReaCtion extends GaPP-Class with the addition of a Markov Chain Monte Carlo kernel applied to each particle permitting track revival and stitching (e.g., within a few time steps after deleting a trajectory). Performance evaluation and benchmarking using synthetic and real data show that GaPP-Class and GaPP-ReaCtion outperform other state-of-the-art tracking algorithms. For example, GaPP-ReaCtion significantly reduces track breaks (e.g., by around 30% from real radar data and markedly more from simulated data).