Kernel-based structural binary pattern tracking

Dae Hwan Kim, Hyo Kak Kim, Seung Jun Lee, Won Jae Park, Sung-Jea Ko

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

In this paper, we propose a new pattern model, called the structural binary pattern (SBP) model, for object tracking. For the proposed SBP model, we introduce an alternate thresholding scheme to generate a set of multiple SBPs. The SBP encodes not only the binary pattern consisting of binarized differences between the average intensities of subregions within the target region, but also the spatial configuration of the subregions. With the proposed SBP model, we define a metric for similarity between the SBP models from the target and candidate for target localization, which is based on an isotropic kernel weighted Hamming distance. To further improve the tracking performance, we employ a color-based tracking method along with the SBP-based tracking method. The experimental results show that the proposed algorithm exhibits the better performance even when the object being tracked confronts drastic illumination changes, partial occlusion, a similar colored background, or low illumination as compared with conventional tracking methods.

Original languageEnglish
Article number6739132
Pages (from-to)1288-1300
Number of pages13
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume24
Issue number8
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Lighting
Hamming distance
Color

Keywords

  • Illumination change
  • kernel-based tracking
  • local binary pattern
  • mean shift
  • visual object tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Kernel-based structural binary pattern tracking. / Kim, Dae Hwan; Kim, Hyo Kak; Lee, Seung Jun; Park, Won Jae; Ko, Sung-Jea.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 24, No. 8, 6739132, 01.01.2014, p. 1288-1300.

Research output: Contribution to journalArticle

Kim, Dae Hwan ; Kim, Hyo Kak ; Lee, Seung Jun ; Park, Won Jae ; Ko, Sung-Jea. / Kernel-based structural binary pattern tracking. In: IEEE Transactions on Circuits and Systems for Video Technology. 2014 ; Vol. 24, No. 8. pp. 1288-1300.
@article{ae38732f4362430dbf7f9bc1bf5df6c9,
title = "Kernel-based structural binary pattern tracking",
abstract = "In this paper, we propose a new pattern model, called the structural binary pattern (SBP) model, for object tracking. For the proposed SBP model, we introduce an alternate thresholding scheme to generate a set of multiple SBPs. The SBP encodes not only the binary pattern consisting of binarized differences between the average intensities of subregions within the target region, but also the spatial configuration of the subregions. With the proposed SBP model, we define a metric for similarity between the SBP models from the target and candidate for target localization, which is based on an isotropic kernel weighted Hamming distance. To further improve the tracking performance, we employ a color-based tracking method along with the SBP-based tracking method. The experimental results show that the proposed algorithm exhibits the better performance even when the object being tracked confronts drastic illumination changes, partial occlusion, a similar colored background, or low illumination as compared with conventional tracking methods.",
keywords = "Illumination change, kernel-based tracking, local binary pattern, mean shift, visual object tracking",
author = "Kim, {Dae Hwan} and Kim, {Hyo Kak} and Lee, {Seung Jun} and Park, {Won Jae} and Sung-Jea Ko",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/TCSVT.2014.2305514",
language = "English",
volume = "24",
pages = "1288--1300",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Kernel-based structural binary pattern tracking

AU - Kim, Dae Hwan

AU - Kim, Hyo Kak

AU - Lee, Seung Jun

AU - Park, Won Jae

AU - Ko, Sung-Jea

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we propose a new pattern model, called the structural binary pattern (SBP) model, for object tracking. For the proposed SBP model, we introduce an alternate thresholding scheme to generate a set of multiple SBPs. The SBP encodes not only the binary pattern consisting of binarized differences between the average intensities of subregions within the target region, but also the spatial configuration of the subregions. With the proposed SBP model, we define a metric for similarity between the SBP models from the target and candidate for target localization, which is based on an isotropic kernel weighted Hamming distance. To further improve the tracking performance, we employ a color-based tracking method along with the SBP-based tracking method. The experimental results show that the proposed algorithm exhibits the better performance even when the object being tracked confronts drastic illumination changes, partial occlusion, a similar colored background, or low illumination as compared with conventional tracking methods.

AB - In this paper, we propose a new pattern model, called the structural binary pattern (SBP) model, for object tracking. For the proposed SBP model, we introduce an alternate thresholding scheme to generate a set of multiple SBPs. The SBP encodes not only the binary pattern consisting of binarized differences between the average intensities of subregions within the target region, but also the spatial configuration of the subregions. With the proposed SBP model, we define a metric for similarity between the SBP models from the target and candidate for target localization, which is based on an isotropic kernel weighted Hamming distance. To further improve the tracking performance, we employ a color-based tracking method along with the SBP-based tracking method. The experimental results show that the proposed algorithm exhibits the better performance even when the object being tracked confronts drastic illumination changes, partial occlusion, a similar colored background, or low illumination as compared with conventional tracking methods.

KW - Illumination change

KW - kernel-based tracking

KW - local binary pattern

KW - mean shift

KW - visual object tracking

UR - http://www.scopus.com/inward/record.url?scp=84905685580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905685580&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2014.2305514

DO - 10.1109/TCSVT.2014.2305514

M3 - Article

AN - SCOPUS:84905685580

VL - 24

SP - 1288

EP - 1300

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 8

M1 - 6739132

ER -