In this section
@inproceedings{Gebru:2017:10.1109/HSCMA.2017.7895564,
author = {Gebru, ID and Evers, C and Naylor, PA and Horaud, R},
doi = {10.1109/HSCMA.2017.7895564},
pages = {71--75},
publisher = {IEEE},
title = {Audio-visual tracking by density approximation in a sequential Bayesian filtering framework},
url = {http://dx.doi.org/10.1109/HSCMA.2017.7895564},
year = {2017}
}
TY - CPAPER
AB - This paper proposes a novel audio-visual 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 audio-visual approach compared to two benchmark visual trackers.
AU - Gebru,ID
AU - Evers,C
AU - Naylor,PA
AU - Horaud,R
DO - 10.1109/HSCMA.2017.7895564
EP - 75
PB - IEEE
PY - 2017///
SP - 71
TI - Audio-visual tracking by density approximation in a sequential Bayesian filtering framework
UR - http://dx.doi.org/10.1109/HSCMA.2017.7895564
UR - http://hdl.handle.net/10044/1/44900
ER -
Speech and Audio Processing Lab
CSP Group, EEE Department
Imperial College London
Exhibition Road, London, SW7 2AZ, United Kingdom