Section: New Results

Visual Tracking of Multiple Persons

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 [4]. The method was combined with visual servoing and implemented on our robot platform (Fig. 3) [38].

Websites:

https://team.inria.fr/perception/research/ovbt/

https://team.inria.fr/perception/research/mot-servoing/

Figure 3. The multi-person tracking method is combined with a visual servoing module. The latter estimates the optimal robot commands and the expected impact of the tracked person locations. The multi-person tracking module refines the locations of the persons with the new observations and the information provided by the visual servoing.