Tracking Multiple Persons Based on a Variational Bayesian Model

Yutong Ban 1 Sileye Ba 1, 2 Xavier Alameda-Pineda 3 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : 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 paper, 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 due 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. The proposed method is benchmarked using the MOT 2016 dataset.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [26 references]  Display  Hide  Download


https://hal.inria.fr/hal-01359559
Contributor : Team Perception <>
Submitted on : Friday, September 2, 2016 - 4:24:13 PM
Last modification on : Wednesday, April 11, 2018 - 1:57:52 AM

Files

eccv2016submission.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Yutong Ban, Sileye Ba, Xavier Alameda-Pineda, Radu Horaud. Tracking Multiple Persons Based on a Variational Bayesian Model. Computer Vision – ECCV 2016 Workshops, Oct 2016, Amsterdam, Netherlands. pp.52-67, ⟨10.1007/978-3-319-48881-3_5⟩. ⟨hal-01359559v2⟩

Share

Metrics

Record views

725

Files downloads

859