Robust tracking of appearance by sparse template adaptation

Takeshi Shakunaga, Kiyoshi Noguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

The problem of real-time tracking appearances in dense visual clutter is challenging. This paper provides a solution to the tough problem by combining an adaptive appearance model and a template-based condensation tracker. As an adaptive appearance model, we utilize the WSL appearance model proposed by Jepson et al. We adopt the sparse template condensation proposed by Shakunaga et al. as a framework of real-time tracking. Rapid and reliable tracking is performed in the framework by matching only a few percent of the whole pixels in the template. Since a sparse template is made up from the stable component of the WSL template, which is called the S-template in this paper, the WSL model and the sparse condensation tracker can collaborate with each other through the sparse S-template. The tracker works as almost rapidly as the sparse template condensation since the WSL model efficiently facilitates the template adaptation.

Original languageEnglish
Title of host publicationProceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006
Pages85-90
Number of pages6
Publication statusPublished - 2006
Event8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006 - Honolulu, HI, United States
Duration: Aug 14 2006Aug 16 2006

Other

Other8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006
CountryUnited States
CityHonolulu, HI
Period8/14/068/16/06

Fingerprint

Condensation
Pixels

Keywords

  • Condensation
  • Object tracking
  • Sparse template matching
  • WSL model

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Shakunaga, T., & Noguchi, K. (2006). Robust tracking of appearance by sparse template adaptation. In Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006 (pp. 85-90)

Robust tracking of appearance by sparse template adaptation. / Shakunaga, Takeshi; Noguchi, Kiyoshi.

Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. 2006. p. 85-90.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shakunaga, T & Noguchi, K 2006, Robust tracking of appearance by sparse template adaptation. in Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. pp. 85-90, 8th IASTED International Conference on Signal and Image Processing, SIP 2006 and the 10th IASTED International Conference on Internet and Multimedia Systems and Applications, IMSA 2006, Honolulu, HI, United States, 8/14/06.
Shakunaga T, Noguchi K. Robust tracking of appearance by sparse template adaptation. In Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. 2006. p. 85-90
Shakunaga, Takeshi ; Noguchi, Kiyoshi. / Robust tracking of appearance by sparse template adaptation. Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006. 2006. pp. 85-90
@inproceedings{42a789d18bb745198c5fd1b4543211d9,
title = "Robust tracking of appearance by sparse template adaptation",
abstract = "The problem of real-time tracking appearances in dense visual clutter is challenging. This paper provides a solution to the tough problem by combining an adaptive appearance model and a template-based condensation tracker. As an adaptive appearance model, we utilize the WSL appearance model proposed by Jepson et al. We adopt the sparse template condensation proposed by Shakunaga et al. as a framework of real-time tracking. Rapid and reliable tracking is performed in the framework by matching only a few percent of the whole pixels in the template. Since a sparse template is made up from the stable component of the WSL template, which is called the S-template in this paper, the WSL model and the sparse condensation tracker can collaborate with each other through the sparse S-template. The tracker works as almost rapidly as the sparse template condensation since the WSL model efficiently facilitates the template adaptation.",
keywords = "Condensation, Object tracking, Sparse template matching, WSL model",
author = "Takeshi Shakunaga and Kiyoshi Noguchi",
year = "2006",
language = "English",
isbn = "0889865833",
pages = "85--90",
booktitle = "Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006",

}

TY - GEN

T1 - Robust tracking of appearance by sparse template adaptation

AU - Shakunaga, Takeshi

AU - Noguchi, Kiyoshi

PY - 2006

Y1 - 2006

N2 - The problem of real-time tracking appearances in dense visual clutter is challenging. This paper provides a solution to the tough problem by combining an adaptive appearance model and a template-based condensation tracker. As an adaptive appearance model, we utilize the WSL appearance model proposed by Jepson et al. We adopt the sparse template condensation proposed by Shakunaga et al. as a framework of real-time tracking. Rapid and reliable tracking is performed in the framework by matching only a few percent of the whole pixels in the template. Since a sparse template is made up from the stable component of the WSL template, which is called the S-template in this paper, the WSL model and the sparse condensation tracker can collaborate with each other through the sparse S-template. The tracker works as almost rapidly as the sparse template condensation since the WSL model efficiently facilitates the template adaptation.

AB - The problem of real-time tracking appearances in dense visual clutter is challenging. This paper provides a solution to the tough problem by combining an adaptive appearance model and a template-based condensation tracker. As an adaptive appearance model, we utilize the WSL appearance model proposed by Jepson et al. We adopt the sparse template condensation proposed by Shakunaga et al. as a framework of real-time tracking. Rapid and reliable tracking is performed in the framework by matching only a few percent of the whole pixels in the template. Since a sparse template is made up from the stable component of the WSL template, which is called the S-template in this paper, the WSL model and the sparse condensation tracker can collaborate with each other through the sparse S-template. The tracker works as almost rapidly as the sparse template condensation since the WSL model efficiently facilitates the template adaptation.

KW - Condensation

KW - Object tracking

KW - Sparse template matching

KW - WSL model

UR - http://www.scopus.com/inward/record.url?scp=56549097378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56549097378&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0889865833

SN - 9780889865839

SP - 85

EP - 90

BT - Proceedings of the 8th IASTED International Conference on Signal and Image Processing, SIP 2006

ER -