Multiple people tracking based on temporal color feature

Seonghoon Kang, Bon W. Hwang, Seong Whan Lee

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

We present a method for detecting and tracking multiple people totally occluded or out of sight in a scene for some period of time in image sequences. Our approach is to use time weighted color information (i.e. the temporal color) for robust medium-term people tracking. The temporal color is the set of pairs of a color value and its associated weights. The weight is related to the size, duration and frequency of appearance of the color region, as well as the number of people adjacent to the target person. It assures our system to continuously track people moving in a group with occlusion. Most systems have built an appearance model for each person to solve occlusion problems. The appearance model contains certain information on the target person - color, shape, texture, position, velocity and face pattern. We use temporal color in the appearance model for the identification of the people occluded or out of sight in the scene upon their reappearance. Experimental results show that the temporal color is more stable than shape or intensity in various cases.

Original languageEnglish
Pages (from-to)931-949
Number of pages19
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume17
Issue number6
DOIs
Publication statusPublished - 2003 Sep 1

Fingerprint

Color
Identification (control systems)
Textures

Keywords

  • Appearance model
  • Human activity recognition
  • Multiple object tracking
  • Multiple people detection
  • Temporal color
  • Visual surveillance

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering

Cite this

Multiple people tracking based on temporal color feature. / Kang, Seonghoon; Hwang, Bon W.; Lee, Seong Whan.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 17, No. 6, 01.09.2003, p. 931-949.

Research output: Contribution to journalArticle

@article{c3e01a3ee5094316b402f50f0a639793,
title = "Multiple people tracking based on temporal color feature",
abstract = "We present a method for detecting and tracking multiple people totally occluded or out of sight in a scene for some period of time in image sequences. Our approach is to use time weighted color information (i.e. the temporal color) for robust medium-term people tracking. The temporal color is the set of pairs of a color value and its associated weights. The weight is related to the size, duration and frequency of appearance of the color region, as well as the number of people adjacent to the target person. It assures our system to continuously track people moving in a group with occlusion. Most systems have built an appearance model for each person to solve occlusion problems. The appearance model contains certain information on the target person - color, shape, texture, position, velocity and face pattern. We use temporal color in the appearance model for the identification of the people occluded or out of sight in the scene upon their reappearance. Experimental results show that the temporal color is more stable than shape or intensity in various cases.",
keywords = "Appearance model, Human activity recognition, Multiple object tracking, Multiple people detection, Temporal color, Visual surveillance",
author = "Seonghoon Kang and Hwang, {Bon W.} and Lee, {Seong Whan}",
year = "2003",
month = "9",
day = "1",
doi = "10.1142/S0218001403002708",
language = "English",
volume = "17",
pages = "931--949",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "6",

}

TY - JOUR

T1 - Multiple people tracking based on temporal color feature

AU - Kang, Seonghoon

AU - Hwang, Bon W.

AU - Lee, Seong Whan

PY - 2003/9/1

Y1 - 2003/9/1

N2 - We present a method for detecting and tracking multiple people totally occluded or out of sight in a scene for some period of time in image sequences. Our approach is to use time weighted color information (i.e. the temporal color) for robust medium-term people tracking. The temporal color is the set of pairs of a color value and its associated weights. The weight is related to the size, duration and frequency of appearance of the color region, as well as the number of people adjacent to the target person. It assures our system to continuously track people moving in a group with occlusion. Most systems have built an appearance model for each person to solve occlusion problems. The appearance model contains certain information on the target person - color, shape, texture, position, velocity and face pattern. We use temporal color in the appearance model for the identification of the people occluded or out of sight in the scene upon their reappearance. Experimental results show that the temporal color is more stable than shape or intensity in various cases.

AB - We present a method for detecting and tracking multiple people totally occluded or out of sight in a scene for some period of time in image sequences. Our approach is to use time weighted color information (i.e. the temporal color) for robust medium-term people tracking. The temporal color is the set of pairs of a color value and its associated weights. The weight is related to the size, duration and frequency of appearance of the color region, as well as the number of people adjacent to the target person. It assures our system to continuously track people moving in a group with occlusion. Most systems have built an appearance model for each person to solve occlusion problems. The appearance model contains certain information on the target person - color, shape, texture, position, velocity and face pattern. We use temporal color in the appearance model for the identification of the people occluded or out of sight in the scene upon their reappearance. Experimental results show that the temporal color is more stable than shape or intensity in various cases.

KW - Appearance model

KW - Human activity recognition

KW - Multiple object tracking

KW - Multiple people detection

KW - Temporal color

KW - Visual surveillance

UR - http://www.scopus.com/inward/record.url?scp=0142118209&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0142118209&partnerID=8YFLogxK

U2 - 10.1142/S0218001403002708

DO - 10.1142/S0218001403002708

M3 - Article

AN - SCOPUS:0142118209

VL - 17

SP - 931

EP - 949

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 6

ER -