Return to Research

Online Variational Bayesian Tracking

Variational Bayesian Framework for Multi-Person Tracking

Sileye Ba, Yutong Ban, Xavier Alameda-PIneda, Alessio Xompero, and Radu Horaud

Papers | Matlab code | Results

Object tracking is an ubiquitous problem in computer vision with many applications in human-machine and human-robot interaction, augmented reality, driving assistance, surveillance, etc. Although thoroughly investigated, tracking multiple persons remains a challenging and an open problem. In this work, an online variational Bayesian model for multiple-person tracking is proposed. This yields a variational expectation-maximization (VEM) algorithm. The computational efficiency of the proposed method is made possible thanks to closed-form expressions for both the posterior distributions of the latent variables and for the estimation of the model parameters. A stochastic process that handles person birth and person death enables the tracker to handle a varying number of persons over long periods of time.

Detections (Observations) on MOT Challenge dataset

Tracking results on MOT Challenge dataset


Sileye Ba, Xavier Alameda-Pineda, Alessio Xompero, Radu Horaud.  An On-line Variational Bayesian Model for Multi-Person Tracking from Cluttered Scenes. Computer Vision and Image Understanding, 2016, 153, pp.64-76. <10.1016/j.cviu.2016.07.006> BibTex

Yutong Ban, Sileye Ba, Xavier Alameda-Pineda, Radu Horaud. Tracking Multiple Persons Based on a Variational Bayesian Model. ECCV Workshop on Benchmarking Mutliple Object Tracking, Oct 2016, Amsterdam, Netherlands. BibTex

Matlab code (coming soon)


Official benchmark results of the MOTChallenge 2016

Detailed results obtained with the MOT’16 dataset : OVBT Tracker