GPU Accelerated ACF Detector

Wiebe Van Ranst, Floris De Smedt, Toon Goedemé

2018

Abstract

The field of pedestrian detection has come a long way in recent decades. In terms of accuracy, the current state-of-the-art is hands down reached by Deep Learning methods. However in terms of running speed this is not always the case, traditional methods are often still faster than their Deep Learning counterparts. This is especially true on embedded hardware, embedded platforms are often used in applications that require realtime performance while at same the time having to make do with a limited amount of resources. In this paper we present a GPU implementation of the ACF pedestrian detector and compare it to current Deep Learning approaches (YOLO) on both a desktop GPU as well as the Jetson TX2 embedded GPU platform.

Paper Citation

in Harvard Style

Van Ranst W., De Smedt F. and Goedemé T. (2018). GPU Accelerated ACF Detector. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 242-248. DOI: 10.5220/0006585102420248

in Bibtex Style

@conference{visapp18,
author={Wiebe Van Ranst and Floris De Smedt and Toon Goedemé},
title={GPU Accelerated ACF Detector},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={242-248},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006585102420248},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - GPU Accelerated ACF Detector
SN - 978-989-758-290-5
AU - Van Ranst W.
AU - De Smedt F.
AU - Goedemé T.
PY - 2018
SP - 242
EP - 248
DO - 10.5220/0006585102420248
PB - SciTePress