Mean-Shift and Sparse Sampling Based SMC-PHD Filtering for Audio Informed Visual Speaker Tracking


Introduction

This software package is a Matlab implementation of the adaptive particle filtering algorithms for multi-speaker audio-visual tracking.

The folder "AV-A_PF" contains the following three sub-folders:-

Core_files: contains the implementation of the particle filtering and adaptive particle filtering algorithms for audio-visual multi-speaker tracking together with some baseline methods.

Sample_test: contains examples on how to use these algorithms.

Test_files: containts the comprehensive tests performed for generating the results in the paper referenced below.

Readme: a brief description about the code.

The pdf file of the paper is also included for detailed description about the algorithms.

More details can be found in the following paper:

  • V. Kilic, M. Barnard, W. Wang, and J. Kittler, "Audio assisted robust visual tracking with adaptive particle filtering", IEEE Transactions on Multimedia, vol. 17, no. 2, pp. 186-200, 2015. [PDF]

    Download

    The Matlab software package can be downloaded from here (4.4Mbytes).

    Written by Volkan Kilic, moderated by Wenwu Wang, version 1.0

    If you have any questions or comments regarding this package, or if you want to report any bugs or unexpected error messages, please send an e-mail to volkan.kilic@ikc.edu.tr or w.wang@surrey.ac.uk

    Copyright 2015 V. Kilic, M. Barnard, W. Wang, and J. Kittler

    This software is a free software distributed under the terms of the GNU Public License version 3 (http://www.gnu.org/licenses/gpl.txt). You can redistribute it and/or modify it under the terms of this licence, for personal and non-commercial use and research purpose.

    References

  • V. Kilic, M. Barnard, W. Wang, and J. Kittler, "Audio assisted robust visual tracking with adaptive particle filtering", IEEE Transactions on Multimedia, vol. 17, no. 2, pp. 186-200, 2015. [PDF]


    [Home] [Publications] [Research] [Teaching] [Short Bio] [Demo & Data] [Codes]

    Last updated on 05 April 2017
    First Created on 05 April 2017