Video object tracking based on a chamfer distance transform

Chen Zezhi; Zsolt L. Husz; Iain Wallace; Andrew M. Wallace

doi:10.1109/ICIP.2007.4379320

Video object tracking based on a chamfer distance transform

Chen Zezhi, Zsolt L. Husz, Iain Wallace, Andrew M. Wallace

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

This paper describes the use of variable kernels based on the normalized Chamfer distance transform (NCDT) for mean shift, object tracking in colour video sequences. This replaces the more usual Epanechnikov kernel, improving target representation and localization without increasing the processing time, minimising the distance between successive frame RGB distributions using the Bhattacharya coefficient. The target shape which defines the NCDT is found either by regional segmentation or background-difference imaging, dependent on the nature of the video sequence. The improved performance is demonstrated on a number of colour video sequences. ©2007 IEEE.

Original language	English
Title of host publication	2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
Pages	III357-III360
Volume	3
DOIs	https://doi.org/10.1109/ICIP.2007.4379320
Publication status	Published - 2006
Event	14th IEEE International Conference on Image Processing 2007 - San Antonio, TX, United States Duration: 16 Sept 2007 → 19 Sept 2007

Conference

Conference	14th IEEE International Conference on Image Processing 2007
Abbreviated title	ICIP 2007
Country/Territory	United States
City	San Antonio, TX
Period	16/09/07 → 19/09/07

Keywords

Bhattacharyya coefficient
Chamfer distance transform
Image segmentation
Mean shift
Object tracking

Access to Document

10.1109/ICIP.2007.4379320

Cite this

@inproceedings{37d064efcb4b489ca8605abaa519919b,

title = "Video object tracking based on a chamfer distance transform",

abstract = "This paper describes the use of variable kernels based on the normalized Chamfer distance transform (NCDT) for mean shift, object tracking in colour video sequences. This replaces the more usual Epanechnikov kernel, improving target representation and localization without increasing the processing time, minimising the distance between successive frame RGB distributions using the Bhattacharya coefficient. The target shape which defines the NCDT is found either by regional segmentation or background-difference imaging, dependent on the nature of the video sequence. The improved performance is demonstrated on a number of colour video sequences. {\textcopyright}2007 IEEE.",

keywords = "Bhattacharyya coefficient, Chamfer distance transform, Image segmentation, Mean shift, Object tracking",

author = "Chen Zezhi and Husz, {Zsolt L.} and Iain Wallace and Wallace, {Andrew M.}",

year = "2006",

doi = "10.1109/ICIP.2007.4379320",

language = "English",

isbn = "1424414377",

volume = "3",

pages = "III357--III360",

booktitle = "2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings",

note = "14th IEEE International Conference on Image Processing 2007, ICIP 2007 ; Conference date: 16-09-2007 Through 19-09-2007",

}

TY - GEN

T1 - Video object tracking based on a chamfer distance transform

AU - Zezhi, Chen

AU - Husz, Zsolt L.

AU - Wallace, Iain

AU - Wallace, Andrew M.

PY - 2006

Y1 - 2006

N2 - This paper describes the use of variable kernels based on the normalized Chamfer distance transform (NCDT) for mean shift, object tracking in colour video sequences. This replaces the more usual Epanechnikov kernel, improving target representation and localization without increasing the processing time, minimising the distance between successive frame RGB distributions using the Bhattacharya coefficient. The target shape which defines the NCDT is found either by regional segmentation or background-difference imaging, dependent on the nature of the video sequence. The improved performance is demonstrated on a number of colour video sequences. ©2007 IEEE.

AB - This paper describes the use of variable kernels based on the normalized Chamfer distance transform (NCDT) for mean shift, object tracking in colour video sequences. This replaces the more usual Epanechnikov kernel, improving target representation and localization without increasing the processing time, minimising the distance between successive frame RGB distributions using the Bhattacharya coefficient. The target shape which defines the NCDT is found either by regional segmentation or background-difference imaging, dependent on the nature of the video sequence. The improved performance is demonstrated on a number of colour video sequences. ©2007 IEEE.

KW - Bhattacharyya coefficient

KW - Chamfer distance transform

KW - Image segmentation

KW - Mean shift

KW - Object tracking

UR - http://www.scopus.com/inward/record.url?scp=48149088332&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2007.4379320

DO - 10.1109/ICIP.2007.4379320

M3 - Conference contribution

SN - 1424414377

SN - 9781424414376

VL - 3

SP - III357-III360

BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings

T2 - 14th IEEE International Conference on Image Processing 2007

Y2 - 16 September 2007 through 19 September 2007

ER -

Video object tracking based on a chamfer distance transform

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this