An On-line Variational Bayesian Model for Multi-Person Tracking from Cluttered Scenes

TL;DR

This paper introduces an online variational Bayesian approach for tracking an unknown and varying number of persons in cluttered scenes, leveraging multiple detectors and modeling appearance/disappearance dynamics.

Contribution

It presents a novel variational Bayesian framework with a VEM algorithm for multi-person tracking that handles unknown numbers and incorporates object birth and death processes.

Findings

Competitive performance on standard datasets.

Effective handling of person appearance and disappearance.

Utilizes multimodal observations from multiple detectors.

Abstract

Object tracking is an ubiquitous problem that appears in many applications such as remote sensing, audio processing, computer vision, human-machine interfaces, human-robot interaction, etc. Although thoroughly investigated in computer vision, tracking a time-varying number of persons remains a challenging open problem. In this paper, we propose an on-line variational Bayesian model for multi-person tracking from cluttered visual observations provided by person detectors. The contributions of this paper are the followings. First, we propose a variational Bayesian framework for tracking an unknown and varying number of persons. Second, our model results in a variational expectation-maximization (VEM) algorithm with closed-form expressions for the posterior distributions of the latent variables and for the estimation of the model parameters. Third, the proposed model exploits observations from multiple detectors, and it is therefore multimodal by nature. Finally, we propose to embed both object-birth and object-visibility processes in an effort to robustly handle person appearances and disappearances over time. Evaluated on classical multiple person tracking datasets, our method shows competitive results with respect to state-of-the-art multiple-object tracking models, such as the probability hypothesis density (PHD) filter among others.