Pedestrian detection and tracking at crossroads

Chia Jung Pai, Hsiao Rong Tyan, Yu Ming Liang, Hong Yuan Mark Liao, Sei Wang Chen

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.

Original languageEnglish
Pages (from-to)1025-1034
Number of pages10
JournalPattern Recognition
Volume37
Issue number5
DOIs
Publication statusPublished - 2004 May 1

Fingerprint

Highway accidents

Keywords

  • Intelligent transportation system
  • Pedestrian detection and tracking
  • Pedestrian model
  • Walking rhythm

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Pai, C. J., Tyan, H. R., Liang, Y. M., Liao, H. Y. M., & Chen, S. W. (2004). Pedestrian detection and tracking at crossroads. Pattern Recognition, 37(5), 1025-1034. https://doi.org/10.1016/j.patcog.2003.10.005

Pedestrian detection and tracking at crossroads. / Pai, Chia Jung; Tyan, Hsiao Rong; Liang, Yu Ming; Liao, Hong Yuan Mark; Chen, Sei Wang.

In: Pattern Recognition, Vol. 37, No. 5, 01.05.2004, p. 1025-1034.

Research output: Contribution to journalArticle

Pai, CJ, Tyan, HR, Liang, YM, Liao, HYM & Chen, SW 2004, 'Pedestrian detection and tracking at crossroads', Pattern Recognition, vol. 37, no. 5, pp. 1025-1034. https://doi.org/10.1016/j.patcog.2003.10.005
Pai, Chia Jung ; Tyan, Hsiao Rong ; Liang, Yu Ming ; Liao, Hong Yuan Mark ; Chen, Sei Wang. / Pedestrian detection and tracking at crossroads. In: Pattern Recognition. 2004 ; Vol. 37, No. 5. pp. 1025-1034.
@article{0fe6951399174a4f85b24414d8151d3b,
title = "Pedestrian detection and tracking at crossroads",
abstract = "This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.",
keywords = "Intelligent transportation system, Pedestrian detection and tracking, Pedestrian model, Walking rhythm",
author = "Pai, {Chia Jung} and Tyan, {Hsiao Rong} and Liang, {Yu Ming} and Liao, {Hong Yuan Mark} and Chen, {Sei Wang}",
year = "2004",
month = "5",
day = "1",
doi = "10.1016/j.patcog.2003.10.005",
language = "English",
volume = "37",
pages = "1025--1034",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Pedestrian detection and tracking at crossroads

AU - Pai, Chia Jung

AU - Tyan, Hsiao Rong

AU - Liang, Yu Ming

AU - Liao, Hong Yuan Mark

AU - Chen, Sei Wang

PY - 2004/5/1

Y1 - 2004/5/1

N2 - This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.

AB - This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.

KW - Intelligent transportation system

KW - Pedestrian detection and tracking

KW - Pedestrian model

KW - Walking rhythm

UR - http://www.scopus.com/inward/record.url?scp=1842865636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1842865636&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2003.10.005

DO - 10.1016/j.patcog.2003.10.005

M3 - Article

AN - SCOPUS:1842865636

VL - 37

SP - 1025

EP - 1034

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 5

ER -