15 Citations (Scopus)

Abstract

Person re-identification across different surveillance cameras with disjoint fields of view has become one of the most interesting and challenging subjects in the area of intelligent video surveillance. Although several methods have been developed and proposed, certain limitations and unresolved issues remain. In all of the existing re-identification approaches, feature vectors are extracted from segmented still images or video frames. Different similarity or dissimilarity measures have been applied to these vectors. Some methods have used simple constant metrics, whereas others have utilised models to obtain optimised metrics. Some have created models based on local colour or texture information, and others have built models based on the gait of people. In general, the main objective of all these approaches is to achieve a higher-accuracy rate and lowercomputational costs. This study summarises several developments in recent literature and discusses the various available methods used in person re-identification. Specifically, their advantages and disadvantages are mentioned and compared.

Original languageEnglish
Pages (from-to)455-474
Number of pages20
JournalIET Computer Vision
Volume8
Issue number6
DOIs
Publication statusPublished - 1 Dec 2014

Fingerprint

Textures
Cameras
Color
Costs

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Review of person re-identification techniques. / Saghafi, Mohammad Ali; Hussain, Aini; Badioze Zaman, Halimah; Md Saad, Mohamad Hanif.

In: IET Computer Vision, Vol. 8, No. 6, 01.12.2014, p. 455-474.

Research output: Contribution to journalArticle

@article{7ee8404dd7474f27bcfc5f046208a2de,
title = "Review of person re-identification techniques",
abstract = "Person re-identification across different surveillance cameras with disjoint fields of view has become one of the most interesting and challenging subjects in the area of intelligent video surveillance. Although several methods have been developed and proposed, certain limitations and unresolved issues remain. In all of the existing re-identification approaches, feature vectors are extracted from segmented still images or video frames. Different similarity or dissimilarity measures have been applied to these vectors. Some methods have used simple constant metrics, whereas others have utilised models to obtain optimised metrics. Some have created models based on local colour or texture information, and others have built models based on the gait of people. In general, the main objective of all these approaches is to achieve a higher-accuracy rate and lowercomputational costs. This study summarises several developments in recent literature and discusses the various available methods used in person re-identification. Specifically, their advantages and disadvantages are mentioned and compared.",
author = "Saghafi, {Mohammad Ali} and Aini Hussain and {Badioze Zaman}, Halimah and {Md Saad}, {Mohamad Hanif}",
year = "2014",
month = "12",
day = "1",
doi = "10.1049/iet-cvi.2013.0180",
language = "English",
volume = "8",
pages = "455--474",
journal = "IET Computer Vision",
issn = "1751-9632",
publisher = "Institution of Engineering and Technology",
number = "6",

}

TY - JOUR

T1 - Review of person re-identification techniques

AU - Saghafi, Mohammad Ali

AU - Hussain, Aini

AU - Badioze Zaman, Halimah

AU - Md Saad, Mohamad Hanif

PY - 2014/12/1

Y1 - 2014/12/1

N2 - Person re-identification across different surveillance cameras with disjoint fields of view has become one of the most interesting and challenging subjects in the area of intelligent video surveillance. Although several methods have been developed and proposed, certain limitations and unresolved issues remain. In all of the existing re-identification approaches, feature vectors are extracted from segmented still images or video frames. Different similarity or dissimilarity measures have been applied to these vectors. Some methods have used simple constant metrics, whereas others have utilised models to obtain optimised metrics. Some have created models based on local colour or texture information, and others have built models based on the gait of people. In general, the main objective of all these approaches is to achieve a higher-accuracy rate and lowercomputational costs. This study summarises several developments in recent literature and discusses the various available methods used in person re-identification. Specifically, their advantages and disadvantages are mentioned and compared.

AB - Person re-identification across different surveillance cameras with disjoint fields of view has become one of the most interesting and challenging subjects in the area of intelligent video surveillance. Although several methods have been developed and proposed, certain limitations and unresolved issues remain. In all of the existing re-identification approaches, feature vectors are extracted from segmented still images or video frames. Different similarity or dissimilarity measures have been applied to these vectors. Some methods have used simple constant metrics, whereas others have utilised models to obtain optimised metrics. Some have created models based on local colour or texture information, and others have built models based on the gait of people. In general, the main objective of all these approaches is to achieve a higher-accuracy rate and lowercomputational costs. This study summarises several developments in recent literature and discusses the various available methods used in person re-identification. Specifically, their advantages and disadvantages are mentioned and compared.

UR - http://www.scopus.com/inward/record.url?scp=84915751281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84915751281&partnerID=8YFLogxK

U2 - 10.1049/iet-cvi.2013.0180

DO - 10.1049/iet-cvi.2013.0180

M3 - Article

AN - SCOPUS:84915751281

VL - 8

SP - 455

EP - 474

JO - IET Computer Vision

JF - IET Computer Vision

SN - 1751-9632

IS - 6

ER -