GPU ACCELERATED REAL-TIME OBJECT DETECTION ON HIGH RESOLUTION VIDEOS USING MODIFIED CENSUS TRANSFORM

Salih Cihan Tek, Muhittin Gökmen

2012

Abstract

This paper presents a novel GPU accelerated object detection system using CUDA. Because of its detection accuracy, speed and robustness to illumination variations, a boosting based approach with Modified Census Transform features is used. Results are given on the face detection problem for evaluation. Results show that even our single-GPU implementation can run in real-time on high resolution video streams without sacrificing accuracy and outperforms the single-threaded and multi-threaded CPU implementations for resolutions ranging from 640×480 to 1920×1080 by a factor of 12-18x and 4-6x, respectively.

Paper Citation

in Harvard Style

Cihan Tek S. and Gökmen M. (2012). GPU ACCELERATED REAL-TIME OBJECT DETECTION ON HIGH RESOLUTION VIDEOS USING MODIFIED CENSUS TRANSFORM . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 685-688. DOI: 10.5220/0003821606850688

in Bibtex Style

@conference{visapp12,
author={Salih Cihan Tek and Muhittin Gökmen},
title={GPU ACCELERATED REAL-TIME OBJECT DETECTION ON HIGH RESOLUTION VIDEOS USING MODIFIED CENSUS TRANSFORM},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={685-688},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003821606850688},
isbn={978-989-8565-03-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - GPU ACCELERATED REAL-TIME OBJECT DETECTION ON HIGH RESOLUTION VIDEOS USING MODIFIED CENSUS TRANSFORM
SN - 978-989-8565-03-7
AU - Cihan Tek S.
AU - Gökmen M.
PY - 2012
SP - 685
EP - 688
DO - 10.5220/0003821606850688