Efficient Pedestrian Detection Using Multi-Scale HOG Features with Low Computational Complexity
Summary :
In this paper, an efficient method to reduce computational complexity for pedestrian detection is presented. Since trilinear interpolation is not used, the amount of required operations for histogram of oriented gradient (HOG) feature calculation is significantly reduced. By calculating multi-scale HOG features with integral HOG in a two-stage approach, both high detection rate and speed are achieved in the proposed method.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.2 pp.366-369
- Publication Date
- 2014/02/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E97.D.366
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Soojin KIM
Hankuk University of Foreign Studies
Kyeongsoon CHO
Hankuk University of Foreign Studies
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Soojin KIM, Kyeongsoon CHO, "Efficient Pedestrian Detection Using Multi-Scale HOG Features with Low Computational Complexity" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 2, pp. 366-369, February 2014, doi: 10.1587/transinf.E97.D.366.
Abstract: In this paper, an efficient method to reduce computational complexity for pedestrian detection is presented. Since trilinear interpolation is not used, the amount of required operations for histogram of oriented gradient (HOG) feature calculation is significantly reduced. By calculating multi-scale HOG features with integral HOG in a two-stage approach, both high detection rate and speed are achieved in the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.366/_p
Copy
@ARTICLE{e97-d_2_366,
author={Soojin KIM, Kyeongsoon CHO, },
journal={IEICE TRANSACTIONS on Information},
title={Efficient Pedestrian Detection Using Multi-Scale HOG Features with Low Computational Complexity},
year={2014},
volume={E97-D},
number={2},
pages={366-369},
abstract={In this paper, an efficient method to reduce computational complexity for pedestrian detection is presented. Since trilinear interpolation is not used, the amount of required operations for histogram of oriented gradient (HOG) feature calculation is significantly reduced. By calculating multi-scale HOG features with integral HOG in a two-stage approach, both high detection rate and speed are achieved in the proposed method.},
keywords={},
doi={10.1587/transinf.E97.D.366},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Efficient Pedestrian Detection Using Multi-Scale HOG Features with Low Computational Complexity
T2 - IEICE TRANSACTIONS on Information
SP - 366
EP - 369
AU - Soojin KIM
AU - Kyeongsoon CHO
PY - 2014
DO - 10.1587/transinf.E97.D.366
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2014
AB - In this paper, an efficient method to reduce computational complexity for pedestrian detection is presented. Since trilinear interpolation is not used, the amount of required operations for histogram of oriented gradient (HOG) feature calculation is significantly reduced. By calculating multi-scale HOG features with integral HOG in a two-stage approach, both high detection rate and speed are achieved in the proposed method.
ER -
English
