Visual tracking with online discriminative learning

Se In Jang, Kwontaeg Choi, Youngsung Kim, Beom Seok Oh, Kar Ann Toh

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

2 Citations (Scopus)

Abstract

We treat tracking as a binary classification task in order to distinguish between an object to be tracked and the background. We propose to integrate an online learning based total-error-rate minimization method (OTER) with an observation model of particle filter for visual tracking. The particle filter is modeled using an affine dynamic model and an observation model. The observation model is constructed using the OTER classifier for binary pattern classification. The proposed method is empirically evaluated both qualitatively and quantitatively using several publicly available video sequences.

Original languageEnglish
Title of host publicationICICS 2011 - 8th International Conference on Information, Communications and Signal Processing
DOIs
Publication statusPublished - 2011 Dec 1
Event8th International Conference on Information, Communications and Signal Processing, ICICS 2011 - Singapore, Singapore
Duration: 2011 Dec 132011 Dec 16

Other

Other8th International Conference on Information, Communications and Signal Processing, ICICS 2011
CountrySingapore
CitySingapore
Period11/12/1311/12/16

Fingerprint

Pattern recognition
Dynamic models
Classifiers

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Jang, S. I., Choi, K., Kim, Y., Oh, B. S., & Toh, K. A. (2011). Visual tracking with online discriminative learning. In ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing [6173536] https://doi.org/10.1109/ICICS.2011.6173536
Jang, Se In ; Choi, Kwontaeg ; Kim, Youngsung ; Oh, Beom Seok ; Toh, Kar Ann. / Visual tracking with online discriminative learning. ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing. 2011.
@inproceedings{939143992c18491db614358ad0d131b3,
title = "Visual tracking with online discriminative learning",
abstract = "We treat tracking as a binary classification task in order to distinguish between an object to be tracked and the background. We propose to integrate an online learning based total-error-rate minimization method (OTER) with an observation model of particle filter for visual tracking. The particle filter is modeled using an affine dynamic model and an observation model. The observation model is constructed using the OTER classifier for binary pattern classification. The proposed method is empirically evaluated both qualitatively and quantitatively using several publicly available video sequences.",
author = "Jang, {Se In} and Kwontaeg Choi and Youngsung Kim and Oh, {Beom Seok} and Toh, {Kar Ann}",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/ICICS.2011.6173536",
language = "English",
isbn = "9781457700309",
booktitle = "ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing",

}

Jang, SI, Choi, K, Kim, Y, Oh, BS & Toh, KA 2011, Visual tracking with online discriminative learning. in ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing., 6173536, 8th International Conference on Information, Communications and Signal Processing, ICICS 2011, Singapore, Singapore, 11/12/13. https://doi.org/10.1109/ICICS.2011.6173536

Visual tracking with online discriminative learning. / Jang, Se In; Choi, Kwontaeg; Kim, Youngsung; Oh, Beom Seok; Toh, Kar Ann.

ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing. 2011. 6173536.

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

TY - GEN

T1 - Visual tracking with online discriminative learning

AU - Jang, Se In

AU - Choi, Kwontaeg

AU - Kim, Youngsung

AU - Oh, Beom Seok

AU - Toh, Kar Ann

PY - 2011/12/1

Y1 - 2011/12/1

N2 - We treat tracking as a binary classification task in order to distinguish between an object to be tracked and the background. We propose to integrate an online learning based total-error-rate minimization method (OTER) with an observation model of particle filter for visual tracking. The particle filter is modeled using an affine dynamic model and an observation model. The observation model is constructed using the OTER classifier for binary pattern classification. The proposed method is empirically evaluated both qualitatively and quantitatively using several publicly available video sequences.

AB - We treat tracking as a binary classification task in order to distinguish between an object to be tracked and the background. We propose to integrate an online learning based total-error-rate minimization method (OTER) with an observation model of particle filter for visual tracking. The particle filter is modeled using an affine dynamic model and an observation model. The observation model is constructed using the OTER classifier for binary pattern classification. The proposed method is empirically evaluated both qualitatively and quantitatively using several publicly available video sequences.

UR - http://www.scopus.com/inward/record.url?scp=84860627354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860627354&partnerID=8YFLogxK

U2 - 10.1109/ICICS.2011.6173536

DO - 10.1109/ICICS.2011.6173536

M3 - Conference contribution

SN - 9781457700309

BT - ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing

ER -

Jang SI, Choi K, Kim Y, Oh BS, Toh KA. Visual tracking with online discriminative learning. In ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing. 2011. 6173536 https://doi.org/10.1109/ICICS.2011.6173536