IEICE TRANSACTIONS on Information
Extended Feature Descriptor and Vehicle Motion Model with Tracking-by-Detection for Pedestrian Active Safety
Summary :
The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented. We improve the technology of detecting pedestrians by using the highly accurate images obtained with a monocular camera. In the detection step, we employ ECoHOG as the feature descriptor; it accumulates the integrated gradient intensities. In the tracking step, we apply an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on real roads.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.2 pp.296-304
- Publication Date
- 2014/02/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E97.D.296
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
Hirokatsu KATAOKA
Keio University,Japan Society for the Promotion of Science
Kimimasa TAMURA
Keio University
Kenji IWATA
National Institute of Advanced Industrial Science and Technology (AIST)
Yutaka SATOH
National Institute of Advanced Industrial Science and Technology (AIST)
Yasuhiro MATSUI
National Traffic Safety and Environment Laboratory
Yoshimitsu AOKI
Keio University
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
Hirokatsu KATAOKA, Kimimasa TAMURA, Kenji IWATA, Yutaka SATOH, Yasuhiro MATSUI, Yoshimitsu AOKI, "Extended Feature Descriptor and Vehicle Motion Model with Tracking-by-Detection for Pedestrian Active Safety" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 2, pp. 296-304, February 2014, doi: 10.1587/transinf.E97.D.296.
Abstract: The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented. We improve the technology of detecting pedestrians by using the highly accurate images obtained with a monocular camera. In the detection step, we employ ECoHOG as the feature descriptor; it accumulates the integrated gradient intensities. In the tracking step, we apply an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on real roads.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.296/_p
Copy
@ARTICLE{e97-d_2_296,
author={Hirokatsu KATAOKA, Kimimasa TAMURA, Kenji IWATA, Yutaka SATOH, Yasuhiro MATSUI, Yoshimitsu AOKI, },
journal={IEICE TRANSACTIONS on Information},
title={Extended Feature Descriptor and Vehicle Motion Model with Tracking-by-Detection for Pedestrian Active Safety},
year={2014},
volume={E97-D},
number={2},
pages={296-304},
abstract={The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented. We improve the technology of detecting pedestrians by using the highly accurate images obtained with a monocular camera. In the detection step, we employ ECoHOG as the feature descriptor; it accumulates the integrated gradient intensities. In the tracking step, we apply an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on real roads.},
keywords={},
doi={10.1587/transinf.E97.D.296},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Extended Feature Descriptor and Vehicle Motion Model with Tracking-by-Detection for Pedestrian Active Safety
T2 - IEICE TRANSACTIONS on Information
SP - 296
EP - 304
AU - Hirokatsu KATAOKA
AU - Kimimasa TAMURA
AU - Kenji IWATA
AU - Yutaka SATOH
AU - Yasuhiro MATSUI
AU - Yoshimitsu AOKI
PY - 2014
DO - 10.1587/transinf.E97.D.296
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2014
AB - The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented. We improve the technology of detecting pedestrians by using the highly accurate images obtained with a monocular camera. In the detection step, we employ ECoHOG as the feature descriptor; it accumulates the integrated gradient intensities. In the tracking step, we apply an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on real roads.
ER -
English
