Extended CoHOG and particle filter by improved motion model for pedestrian active safety

Hirokatsu Kataoka, Kimimasa Tamura, Yoshimitsu Aoki, Yasuhiro Matsui

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The percentage of pedestrian deaths in traffic accidents is on the rise. In recent years, there have been calls for measures to be introduced to protect such vulnerable road users as pedestrians and cyclists. In this study, a method to detect pedestrians using an in-vehicle camera is presented. We improved the technology in detecting pedestrians with highly accurate images using a monocular camera. We were able to predict pedestrians' activities by monitoring them, and we developed an algorithm to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we found that an extended co-occurrence histogram of oriented gradients, accumulating the integration of gradient intensities. In tracking step, we applied effective motion model using optical flow for Particle Filter tracking. These techniques are valified by using images captured on the real road.

Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
Pages1511-1516
Number of pages6
DOIs
Publication statusPublished - 2012
Event38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012 - Montreal, QC, Canada
Duration: 2012 Oct 252012 Oct 28

Other

Other38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012
CountryCanada
CityMontreal, QC
Period12/10/2512/10/28

Fingerprint

Cameras
Highway accidents
Optical flows
Monitoring

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kataoka, H., Tamura, K., Aoki, Y., & Matsui, Y. (2012). Extended CoHOG and particle filter by improved motion model for pedestrian active safety. In IECON Proceedings (Industrial Electronics Conference) (pp. 1511-1516). [6388518] https://doi.org/10.1109/IECON.2012.6388518

Extended CoHOG and particle filter by improved motion model for pedestrian active safety. / Kataoka, Hirokatsu; Tamura, Kimimasa; Aoki, Yoshimitsu; Matsui, Yasuhiro.

IECON Proceedings (Industrial Electronics Conference). 2012. p. 1511-1516 6388518.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kataoka, H, Tamura, K, Aoki, Y & Matsui, Y 2012, Extended CoHOG and particle filter by improved motion model for pedestrian active safety. in IECON Proceedings (Industrial Electronics Conference)., 6388518, pp. 1511-1516, 38th Annual Conference on IEEE Industrial Electronics Society, IECON 2012, Montreal, QC, Canada, 12/10/25. https://doi.org/10.1109/IECON.2012.6388518
Kataoka H, Tamura K, Aoki Y, Matsui Y. Extended CoHOG and particle filter by improved motion model for pedestrian active safety. In IECON Proceedings (Industrial Electronics Conference). 2012. p. 1511-1516. 6388518 https://doi.org/10.1109/IECON.2012.6388518
Kataoka, Hirokatsu ; Tamura, Kimimasa ; Aoki, Yoshimitsu ; Matsui, Yasuhiro. / Extended CoHOG and particle filter by improved motion model for pedestrian active safety. IECON Proceedings (Industrial Electronics Conference). 2012. pp. 1511-1516
@inproceedings{cdc75833c9dc4a32992aeaaf976bc3ef,
title = "Extended CoHOG and particle filter by improved motion model for pedestrian active safety",
abstract = "The percentage of pedestrian deaths in traffic accidents is on the rise. In recent years, there have been calls for measures to be introduced to protect such vulnerable road users as pedestrians and cyclists. In this study, a method to detect pedestrians using an in-vehicle camera is presented. We improved the technology in detecting pedestrians with highly accurate images using a monocular camera. We were able to predict pedestrians' activities by monitoring them, and we developed an algorithm to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we found that an extended co-occurrence histogram of oriented gradients, accumulating the integration of gradient intensities. In tracking step, we applied effective motion model using optical flow for Particle Filter tracking. These techniques are valified by using images captured on the real road.",
author = "Hirokatsu Kataoka and Kimimasa Tamura and Yoshimitsu Aoki and Yasuhiro Matsui",
year = "2012",
doi = "10.1109/IECON.2012.6388518",
language = "English",
isbn = "9781467324212",
pages = "1511--1516",
booktitle = "IECON Proceedings (Industrial Electronics Conference)",

}

TY - GEN

T1 - Extended CoHOG and particle filter by improved motion model for pedestrian active safety

AU - Kataoka, Hirokatsu

AU - Tamura, Kimimasa

AU - Aoki, Yoshimitsu

AU - Matsui, Yasuhiro

PY - 2012

Y1 - 2012

N2 - The percentage of pedestrian deaths in traffic accidents is on the rise. In recent years, there have been calls for measures to be introduced to protect such vulnerable road users as pedestrians and cyclists. In this study, a method to detect pedestrians using an in-vehicle camera is presented. We improved the technology in detecting pedestrians with highly accurate images using a monocular camera. We were able to predict pedestrians' activities by monitoring them, and we developed an algorithm to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we found that an extended co-occurrence histogram of oriented gradients, accumulating the integration of gradient intensities. In tracking step, we applied effective motion model using optical flow for Particle Filter tracking. These techniques are valified by using images captured on the real road.

AB - The percentage of pedestrian deaths in traffic accidents is on the rise. In recent years, there have been calls for measures to be introduced to protect such vulnerable road users as pedestrians and cyclists. In this study, a method to detect pedestrians using an in-vehicle camera is presented. We improved the technology in detecting pedestrians with highly accurate images using a monocular camera. We were able to predict pedestrians' activities by monitoring them, and we developed an algorithm to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we found that an extended co-occurrence histogram of oriented gradients, accumulating the integration of gradient intensities. In tracking step, we applied effective motion model using optical flow for Particle Filter tracking. These techniques are valified by using images captured on the real road.

UR - http://www.scopus.com/inward/record.url?scp=84872926384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872926384&partnerID=8YFLogxK

U2 - 10.1109/IECON.2012.6388518

DO - 10.1109/IECON.2012.6388518

M3 - Conference contribution

AN - SCOPUS:84872926384

SN - 9781467324212

SP - 1511

EP - 1516

BT - IECON Proceedings (Industrial Electronics Conference)

ER -