Information Fusion for Action Recognition with Deeply Optimised Hough Transform Paradigm

Geoffrey Vaquette, Catherine Achard, Laurent Lucat

2016

Abstract

Automatic human action recognition is a challenging and largely explored domain. In this work, we focus on action segmentation with Hough Transform paradigm and more precisely with Deeply Optimised Hough Transform (DOHT). First, we apply DOHT on video sequences using the well-known dense trajectories features and then, we propose to extend the method to efficiently merge information coming from various sensors. We have introduced three different ways to perform fusion, depending on the level at which information is merged. Advantages and disadvantages of these solutions are presented from the performance point of view and also according to the ease of use. Thus, one of the fusion level has the advantage to stay suitabe even if one or more sensors is out of order or disturbed.

Paper Citation

in Harvard Style

Vaquette G., Achard C. and Lucat L. (2016). Information Fusion for Action Recognition with Deeply Optimised Hough Transform Paradigm . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 423-430. DOI: 10.5220/0005725604230430

in Bibtex Style

@conference{visapp16,
author={Geoffrey Vaquette and Catherine Achard and Laurent Lucat},
title={Information Fusion for Action Recognition with Deeply Optimised Hough Transform Paradigm},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={423-430},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005725604230430},
isbn={978-989-758-175-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - Information Fusion for Action Recognition with Deeply Optimised Hough Transform Paradigm
SN - 978-989-758-175-5
AU - Vaquette G.
AU - Achard C.
AU - Lucat L.
PY - 2016
SP - 423
EP - 430
DO - 10.5220/0005725604230430