Feature Interaction Descriptor for Pedestrian Detection
Summary :
We propose a novel representation called Feature Interaction Descriptor (FIND) to capture high-level properties of object appearance by computing pairwise interactions of adjacent region-level features. In order to deal with pedestrian detection task, we employ localized oriented gradient histograms as region-level features and measure interactions between adjacent histogram elements with a suitable histogram-similarity function. The experimental results show that our descriptor improves upon HOG significantly and outperforms related high-level features such as GLAC and CoHOG.
- Publication
- IEICE TRANSACTIONS on Information Vol.E93-D No.9 pp.2656-2659
- Publication Date
- 2010/09/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E93.D.2656
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
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
Hui CAO, Koichiro YAMAGUCHI, Mitsuhiko OHTA, Takashi NAITO, Yoshiki NINOMIYA, "Feature Interaction Descriptor for Pedestrian Detection" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 9, pp. 2656-2659, September 2010, doi: 10.1587/transinf.E93.D.2656.
Abstract: We propose a novel representation called Feature Interaction Descriptor (FIND) to capture high-level properties of object appearance by computing pairwise interactions of adjacent region-level features. In order to deal with pedestrian detection task, we employ localized oriented gradient histograms as region-level features and measure interactions between adjacent histogram elements with a suitable histogram-similarity function. The experimental results show that our descriptor improves upon HOG significantly and outperforms related high-level features such as GLAC and CoHOG.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2656/_p
Copy
@ARTICLE{e93-d_9_2656,
author={Hui CAO, Koichiro YAMAGUCHI, Mitsuhiko OHTA, Takashi NAITO, Yoshiki NINOMIYA, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Interaction Descriptor for Pedestrian Detection},
year={2010},
volume={E93-D},
number={9},
pages={2656-2659},
abstract={We propose a novel representation called Feature Interaction Descriptor (FIND) to capture high-level properties of object appearance by computing pairwise interactions of adjacent region-level features. In order to deal with pedestrian detection task, we employ localized oriented gradient histograms as region-level features and measure interactions between adjacent histogram elements with a suitable histogram-similarity function. The experimental results show that our descriptor improves upon HOG significantly and outperforms related high-level features such as GLAC and CoHOG.},
keywords={},
doi={10.1587/transinf.E93.D.2656},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Feature Interaction Descriptor for Pedestrian Detection
T2 - IEICE TRANSACTIONS on Information
SP - 2656
EP - 2659
AU - Hui CAO
AU - Koichiro YAMAGUCHI
AU - Mitsuhiko OHTA
AU - Takashi NAITO
AU - Yoshiki NINOMIYA
PY - 2010
DO - 10.1587/transinf.E93.D.2656
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2010
AB - We propose a novel representation called Feature Interaction Descriptor (FIND) to capture high-level properties of object appearance by computing pairwise interactions of adjacent region-level features. In order to deal with pedestrian detection task, we employ localized oriented gradient histograms as region-level features and measure interactions between adjacent histogram elements with a suitable histogram-similarity function. The experimental results show that our descriptor improves upon HOG significantly and outperforms related high-level features such as GLAC and CoHOG.
ER -
English
