Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection

Hirokatsu Kataoka, Yoshimitsu Aoki

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

2 Citations (Scopus)

Abstract

Pedestrian detection method is the highest priority for "active safety" which prevents traffic accidents before happens. In previous studies, edge orientation based feature descriptors are proposed. Recently, high standard detection algorithm, Co-occurrence Histograms of Oriented Gradients (CoHOG) is proposed. However, this method has miss detection in complicated situation and processing cost is high. We propose symmetrical judgment algorithm and an extended version of CoHOG for high speed and high accuracy pedestrian detection. The effectiveness of the proposed method was proved on pedestrian detection performance test.

Original languageEnglish
Title of host publicationProceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011
Pages536-539
Number of pages4
Publication statusPublished - 2011
Event12th IAPR Conference on Machine Vision Applications, MVA 2011 - Nara, Japan
Duration: 2011 Jun 132011 Jun 15

Other

Other12th IAPR Conference on Machine Vision Applications, MVA 2011
CountryJapan
CityNara
Period11/6/1311/6/15

Fingerprint

Highway accidents
Processing
Costs

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Kataoka, H., & Aoki, Y. (2011). Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection. In Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011 (pp. 536-539)

Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection. / Kataoka, Hirokatsu; Aoki, Yoshimitsu.

Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011. 2011. p. 536-539.

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

Kataoka, H & Aoki, Y 2011, Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection. in Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011. pp. 536-539, 12th IAPR Conference on Machine Vision Applications, MVA 2011, Nara, Japan, 11/6/13.
Kataoka H, Aoki Y. Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection. In Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011. 2011. p. 536-539
Kataoka, Hirokatsu ; Aoki, Yoshimitsu. / Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection. Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011. 2011. pp. 536-539
@inproceedings{0ab24bc8d83b4ec89df96dd8c572f83c,
title = "Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection",
abstract = "Pedestrian detection method is the highest priority for {"}active safety{"} which prevents traffic accidents before happens. In previous studies, edge orientation based feature descriptors are proposed. Recently, high standard detection algorithm, Co-occurrence Histograms of Oriented Gradients (CoHOG) is proposed. However, this method has miss detection in complicated situation and processing cost is high. We propose symmetrical judgment algorithm and an extended version of CoHOG for high speed and high accuracy pedestrian detection. The effectiveness of the proposed method was proved on pedestrian detection performance test.",
author = "Hirokatsu Kataoka and Yoshimitsu Aoki",
year = "2011",
language = "English",
isbn = "9784901122115",
pages = "536--539",
booktitle = "Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011",

}

TY - GEN

T1 - Symmetrical judgment and improvement of CoHOG feature descriptor for pedestrian detection

AU - Kataoka, Hirokatsu

AU - Aoki, Yoshimitsu

PY - 2011

Y1 - 2011

N2 - Pedestrian detection method is the highest priority for "active safety" which prevents traffic accidents before happens. In previous studies, edge orientation based feature descriptors are proposed. Recently, high standard detection algorithm, Co-occurrence Histograms of Oriented Gradients (CoHOG) is proposed. However, this method has miss detection in complicated situation and processing cost is high. We propose symmetrical judgment algorithm and an extended version of CoHOG for high speed and high accuracy pedestrian detection. The effectiveness of the proposed method was proved on pedestrian detection performance test.

AB - Pedestrian detection method is the highest priority for "active safety" which prevents traffic accidents before happens. In previous studies, edge orientation based feature descriptors are proposed. Recently, high standard detection algorithm, Co-occurrence Histograms of Oriented Gradients (CoHOG) is proposed. However, this method has miss detection in complicated situation and processing cost is high. We propose symmetrical judgment algorithm and an extended version of CoHOG for high speed and high accuracy pedestrian detection. The effectiveness of the proposed method was proved on pedestrian detection performance test.

UR - http://www.scopus.com/inward/record.url?scp=84872508470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872508470&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84872508470

SN - 9784901122115

SP - 536

EP - 539

BT - Proceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011

ER -