Improvement CoHOG detection and texture matching tracking for pedestrian's active safety

Hirokatsu Kataoka, Kimimasa Tamura, Yasuhiro Matsui, Yoshimitsu Aoki

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The total number of deaths by traffic accidents was 4,863 in 2010 and the percentage of pedestrians in the deaths tended to increase in Japan. In recent years, to provide measures for accident avoidance has been urgently required for the people on the roads or streets including pedestrians and cyclists, so called "vulnerable road users". In the present study, technologies to detect pedestrians by forward images with cameras installed in vehicles are under development. The purpose in this study is to improve the technologies to detect and track pedestrians with a high degree of accuracy of images with a single camera. In this study, the authors predicted pedestrians' activities by monitoring pedestrians for a given length of time and developed an algorithm to recognize pedestrians and to track the pedestrian movementswith a higher degree of accuracy. The effectiveness of the algorithm was investigated by pedestrians' images on real-world roads. Regarding detecting the pedestrian feature descriptor, the authors newly found that an ECoHOG accumulating the integration of gradient intensities was the best method to decrease both the undetectable and excessive detectable ratio. Therefore, the usage of the new method by images captured on the real road was validated.

Original languageEnglish
Pages (from-to)1108-1115
Number of pages8
JournalIEEJ Transactions on Electronics, Information and Systems
Volume132
Issue number7
DOIs
Publication statusPublished - 2012

Fingerprint

Textures
Cameras
Highway accidents
Accidents
Monitoring

Keywords

  • Active Safety
  • CoHOG
  • Particle Filter
  • Pedestrian Detection
  • Pedestrian Tracking
  • Symmetrical Judgment

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Improvement CoHOG detection and texture matching tracking for pedestrian's active safety. / Kataoka, Hirokatsu; Tamura, Kimimasa; Matsui, Yasuhiro; Aoki, Yoshimitsu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 132, No. 7, 2012, p. 1108-1115.

Research output: Contribution to journalArticle

@article{99b3b975a3ee438c8e2cab17f3ffab70,
title = "Improvement CoHOG detection and texture matching tracking for pedestrian's active safety",
abstract = "The total number of deaths by traffic accidents was 4,863 in 2010 and the percentage of pedestrians in the deaths tended to increase in Japan. In recent years, to provide measures for accident avoidance has been urgently required for the people on the roads or streets including pedestrians and cyclists, so called {"}vulnerable road users{"}. In the present study, technologies to detect pedestrians by forward images with cameras installed in vehicles are under development. The purpose in this study is to improve the technologies to detect and track pedestrians with a high degree of accuracy of images with a single camera. In this study, the authors predicted pedestrians' activities by monitoring pedestrians for a given length of time and developed an algorithm to recognize pedestrians and to track the pedestrian movementswith a higher degree of accuracy. The effectiveness of the algorithm was investigated by pedestrians' images on real-world roads. Regarding detecting the pedestrian feature descriptor, the authors newly found that an ECoHOG accumulating the integration of gradient intensities was the best method to decrease both the undetectable and excessive detectable ratio. Therefore, the usage of the new method by images captured on the real road was validated.",
keywords = "Active Safety, CoHOG, Particle Filter, Pedestrian Detection, Pedestrian Tracking, Symmetrical Judgment",
author = "Hirokatsu Kataoka and Kimimasa Tamura and Yasuhiro Matsui and Yoshimitsu Aoki",
year = "2012",
doi = "10.1541/ieejeiss.132.1108",
language = "English",
volume = "132",
pages = "1108--1115",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "7",

}

TY - JOUR

T1 - Improvement CoHOG detection and texture matching tracking for pedestrian's active safety

AU - Kataoka, Hirokatsu

AU - Tamura, Kimimasa

AU - Matsui, Yasuhiro

AU - Aoki, Yoshimitsu

PY - 2012

Y1 - 2012

N2 - The total number of deaths by traffic accidents was 4,863 in 2010 and the percentage of pedestrians in the deaths tended to increase in Japan. In recent years, to provide measures for accident avoidance has been urgently required for the people on the roads or streets including pedestrians and cyclists, so called "vulnerable road users". In the present study, technologies to detect pedestrians by forward images with cameras installed in vehicles are under development. The purpose in this study is to improve the technologies to detect and track pedestrians with a high degree of accuracy of images with a single camera. In this study, the authors predicted pedestrians' activities by monitoring pedestrians for a given length of time and developed an algorithm to recognize pedestrians and to track the pedestrian movementswith a higher degree of accuracy. The effectiveness of the algorithm was investigated by pedestrians' images on real-world roads. Regarding detecting the pedestrian feature descriptor, the authors newly found that an ECoHOG accumulating the integration of gradient intensities was the best method to decrease both the undetectable and excessive detectable ratio. Therefore, the usage of the new method by images captured on the real road was validated.

AB - The total number of deaths by traffic accidents was 4,863 in 2010 and the percentage of pedestrians in the deaths tended to increase in Japan. In recent years, to provide measures for accident avoidance has been urgently required for the people on the roads or streets including pedestrians and cyclists, so called "vulnerable road users". In the present study, technologies to detect pedestrians by forward images with cameras installed in vehicles are under development. The purpose in this study is to improve the technologies to detect and track pedestrians with a high degree of accuracy of images with a single camera. In this study, the authors predicted pedestrians' activities by monitoring pedestrians for a given length of time and developed an algorithm to recognize pedestrians and to track the pedestrian movementswith a higher degree of accuracy. The effectiveness of the algorithm was investigated by pedestrians' images on real-world roads. Regarding detecting the pedestrian feature descriptor, the authors newly found that an ECoHOG accumulating the integration of gradient intensities was the best method to decrease both the undetectable and excessive detectable ratio. Therefore, the usage of the new method by images captured on the real road was validated.

KW - Active Safety

KW - CoHOG

KW - Particle Filter

KW - Pedestrian Detection

KW - Pedestrian Tracking

KW - Symmetrical Judgment

UR - http://www.scopus.com/inward/record.url?scp=84867057494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867057494&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.132.1108

DO - 10.1541/ieejeiss.132.1108

M3 - Article

AN - SCOPUS:84867057494

VL - 132

SP - 1108

EP - 1115

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 7

ER -