loading
Papers

Research.Publish.Connect.

Paper

Authors: Petr Jecmen 1 ; Frederic Lerasle 2 and Alhayat Ali Mekonnen 2

Affiliations: 1 Technical University of Liberec, Czech Republic ; 2 LAAS-CNRS and Universite de Toulouse, France

ISBN: 978-989-758-227-1

Keyword(s): Particle Filter, MOT, GPGPU, Decentralized Tracking, Multi-template Appearance Model.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Motion, Tracking and Stereo Vision ; Tracking and Visual Navigation ; Video Surveillance and Event Detection

Abstract: In this work, we present the design, analysis and implementation of a decentralized particle filter (DPF) for multiple object tracking (MOT) on a graphics processing unit (GPU). We investigate two variants of the implementation, their advantages and caveats in terms of scaling with larger particle numbers and performance on several datasets. First we compare the precision of our GPU implementation with standard CPU version. Next we compare performance of the GPU variants under different scenarios. The results show the GPU variant leads to a five fold speedup on average (in best cases the speedup reaches a factor of 18) over the CPU variant while keeping similar tracking accuracy and precision.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.171.45.91

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Jecmen, P.; Lerasle, F. and Ali Mekonnen, A. (2017). Trade-off Between GPGPU based Implementations of Multi Object Tracking Particle Filter.In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6 VISAPP: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 123-131. DOI: 10.5220/0006092301230131

@conference{visapp17,
author={Petr Jecmen. and Frederic Lerasle. and Alhayat Ali Mekonnen.},
title={Trade-off Between GPGPU based Implementations of Multi Object Tracking Particle Filter},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6 VISAPP: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={123-131},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006092301230131},
isbn={978-989-758-227-1},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6 VISAPP: VISAPP, (VISIGRAPP 2017)
TI - Trade-off Between GPGPU based Implementations of Multi Object Tracking Particle Filter
SN - 978-989-758-227-1
AU - Jecmen, P.
AU - Lerasle, F.
AU - Ali Mekonnen, A.
PY - 2017
SP - 123
EP - 131
DO - 10.5220/0006092301230131

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.