Audio-visual Tracking by Density Approximation in a Sequential Bayesian Filtering Framework

Israel Gebru 1 Christine Evers 2 Patrick Naylor 2 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 : This paper proposes a novel audiovisual tracking approach that exploits constructively audio and visual modalities in order to estimate trajectories of multiple people in a joint state space. The tracking problem is modeled using a sequential Bayesian filtering framework. Within this framework, we propose to represent the posterior density with a Gaussian Mixture Model (GMM). To ensure that a GMM representation can be retained sequentially over time, the predictive density is approximated by a GMM using the Unscented Transform. While a density interpolation technique is introduced to obtain a continuous representation of the observation likelihood, which is also a GMM. Furthermore, to prevent the number of mixtures from growing exponentially over time, a density approximation based on the Expectation Maximization (EM) algorithm is applied, resulting in a compact GMM representation of the posterior density. Recordings using a camcorder and microphone array are used to evaluate the proposed approach, demonstrating significant improvements in tracking performance of the proposed audiovisual approach compared to two benchmark visual trackers.
Liste complète des métadonnées
Contributor : Team Perception <>
Submitted on : Friday, March 17, 2017 - 3:07:06 PM
Last modification on : Thursday, May 24, 2018 - 5:12:37 PM
Document(s) archivé(s) le : Sunday, June 18, 2017 - 1:28:21 PM


Files produced by the author(s)




Israel Gebru, Christine Evers, Patrick Naylor, Radu Horaud. Audio-visual Tracking by Density Approximation in a Sequential Bayesian Filtering Framework. IEEE Workshop on Hands-free Speech Communication and Microphone Arrays, IEEE Signal Processing Society, Mar 2017, San Francisco, CA, United States. pp.71-75, ⟨10.1109/HSCMA.2017.7895564⟩. ⟨hal-01452167⟩



Record views


Files downloads