Adaptive template matching algorithm based on SWAD for robust target tracking

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The sum of absolute differences (SAD) is widely used in video coding and disparity computation for its simplicity. However, SAD is not very common in tracking applications owing to issues like partial occlusion and target changes, which can dramatically affect its performance. Presented is a novel adaptive template matching algorithm for target tracking, based on a sum of weighted absolute differences (SWAD). The target template is updated using an infinite impulse response filter, while a weighting kernel is adopted to reduce the effects of partial occlusion. Simulation results demonstrate that the proposed tracker outperforms conventional SAD in terms of efficiency and accuracy, and its performance is comparable with more complex trackers, such as the mean shift algorithm
LanguageEnglish
Pages261-262
Number of pages2
JournalElectronics Letters
Volume48
Issue number5
DOIs
Publication statusPublished - 1 Mar 2012

Fingerprint

Template matching
Target tracking
IIR filters
Image coding

Keywords

  • adaptive template
  • matching algorithm
  • SWAD
  • robust target tracking
  • IIR filters
  • target tracking
  • image matching

Cite this

@article{f38f50ecbc2944d8842776eeceaabd59,
title = "Adaptive template matching algorithm based on SWAD for robust target tracking",
abstract = "The sum of absolute differences (SAD) is widely used in video coding and disparity computation for its simplicity. However, SAD is not very common in tracking applications owing to issues like partial occlusion and target changes, which can dramatically affect its performance. Presented is a novel adaptive template matching algorithm for target tracking, based on a sum of weighted absolute differences (SWAD). The target template is updated using an infinite impulse response filter, while a weighting kernel is adopted to reduce the effects of partial occlusion. Simulation results demonstrate that the proposed tracker outperforms conventional SAD in terms of efficiency and accuracy, and its performance is comparable with more complex trackers, such as the mean shift algorithm",
keywords = "adaptive template , matching algorithm, SWAD, robust target tracking, IIR filters, target tracking , image matching",
author = "{Di Caterina}, G. and Soraghan, {J. J.}",
year = "2012",
month = "3",
day = "1",
doi = "10.1049/el.2011.3888",
language = "English",
volume = "48",
pages = "261--262",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "5",

}

Adaptive template matching algorithm based on SWAD for robust target tracking. / Di Caterina, G.; Soraghan, J. J.

In: Electronics Letters, Vol. 48, No. 5, 01.03.2012, p. 261-262.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive template matching algorithm based on SWAD for robust target tracking

AU - Di Caterina, G.

AU - Soraghan, J. J.

PY - 2012/3/1

Y1 - 2012/3/1

N2 - The sum of absolute differences (SAD) is widely used in video coding and disparity computation for its simplicity. However, SAD is not very common in tracking applications owing to issues like partial occlusion and target changes, which can dramatically affect its performance. Presented is a novel adaptive template matching algorithm for target tracking, based on a sum of weighted absolute differences (SWAD). The target template is updated using an infinite impulse response filter, while a weighting kernel is adopted to reduce the effects of partial occlusion. Simulation results demonstrate that the proposed tracker outperforms conventional SAD in terms of efficiency and accuracy, and its performance is comparable with more complex trackers, such as the mean shift algorithm

AB - The sum of absolute differences (SAD) is widely used in video coding and disparity computation for its simplicity. However, SAD is not very common in tracking applications owing to issues like partial occlusion and target changes, which can dramatically affect its performance. Presented is a novel adaptive template matching algorithm for target tracking, based on a sum of weighted absolute differences (SWAD). The target template is updated using an infinite impulse response filter, while a weighting kernel is adopted to reduce the effects of partial occlusion. Simulation results demonstrate that the proposed tracker outperforms conventional SAD in terms of efficiency and accuracy, and its performance is comparable with more complex trackers, such as the mean shift algorithm

KW - adaptive template

KW - matching algorithm

KW - SWAD

KW - robust target tracking

KW - IIR filters

KW - target tracking

KW - image matching

UR - http://www.scopus.com/inward/record.url?scp=84858127371&partnerID=8YFLogxK

U2 - 10.1049/el.2011.3888

DO - 10.1049/el.2011.3888

M3 - Article

VL - 48

SP - 261

EP - 262

JO - Electronics Letters

T2 - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 5

ER -