Visual measurement cues for face tracking

Aristodemos Pnevmatikakis; Andreas Stergiou; Theodoros Petsatodis; Nikolaos Katsarakis

doi:10.1109/ICDSP.2013.6622722

Visual measurement cues for face tracking

Aristodemos Pnevmatikakis, Andreas Stergiou, Theodoros Petsatodis, Nikolaos Katsarakis

Institut for Elektroniske Systemer

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

Abstract

Particle filters allow for visual trackers with nonlinear measurements. In this paper we consider three different non-linear visual measurement cues, based on object detection, foreground segmentation and colour matching. Novel ways to obtain robust measurement likelihoods under a unified representation scheme are discussed, followed by a likelihood combination scheme for fusion. The resulting single and multi-cue particle filter trackers are compared in the scope of face tracking.

Originalsprog	Engelsk
Titel	2013 18th International Conference on Digital Signal Processing, DSP 2013
Antal sider	6
Forlag	IEEE Press
Publikationsdato	6 dec. 2013
Sider	1-6
Artikelnummer	6622722
ISBN (Trykt)	978-146735805-7
ISBN (Elektronisk)	978-1-4673-5807-1
DOI	https://doi.org/10.1109/ICDSP.2013.6622722
Status	Udgivet - 6 dec. 2013
Begivenhed	International conference on Digital Signal Processing - Fira, Grækenland Varighed: 1 jul. 2013 → 3 jul. 2013 Konferencens nummer: 18 http://dsp2013.dspconferences.org/

Konference

Konference	International conference on Digital Signal Processing
Nummer	18
Land/Område	Grækenland
By	Fira
Periode	01/07/2013 → 03/07/2013
Internetadresse	http://dsp2013.dspconferences.org/

Navn	International Conference on Digital Signal Processing proceedings
ISSN	1546-1874

Adgang til dokumentet

10.1109/ICDSP.2013.6622722

http://www.scopus.com/inward/record.url?scp=84888883802&partnerID=8YFLogxK

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Citationsformater

@inproceedings{9f03a0c9fc8646b9a0d8e59770ce7502,

title = "Visual measurement cues for face tracking",

abstract = "Particle filters allow for visual trackers with nonlinear measurements. In this paper we consider three different non-linear visual measurement cues, based on object detection, foreground segmentation and colour matching. Novel ways to obtain robust measurement likelihoods under a unified representation scheme are discussed, followed by a likelihood combination scheme for fusion. The resulting single and multi-cue particle filter trackers are compared in the scope of face tracking.",

keywords = "Face tracking, Fusion, Likelihood function, Particle filters, Visual measurements",

author = "Aristodemos Pnevmatikakis and Andreas Stergiou and Theodoros Petsatodis and Nikolaos Katsarakis",

year = "2013",

month = dec,

day = "6",

doi = "10.1109/ICDSP.2013.6622722",

language = "English",

isbn = "978-146735805-7",

series = "International Conference on Digital Signal Processing proceedings",

pages = "1--6",

booktitle = "2013 18th International Conference on Digital Signal Processing, DSP 2013",

publisher = "IEEE Press",

note = "International conference on Digital Signal Processing ; Conference date: 01-07-2013 Through 03-07-2013",

url = "http://dsp2013.dspconferences.org/",

}

Pnevmatikakis, A, Stergiou, A, Petsatodis, T & Katsarakis, N 2013, Visual measurement cues for face tracking. i 2013 18th International Conference on Digital Signal Processing, DSP 2013., 6622722, IEEE Press, International Conference on Digital Signal Processing proceedings, s. 1-6, International conference on Digital Signal Processing, Fira, Grækenland, 01/07/2013. https://doi.org/10.1109/ICDSP.2013.6622722

Visual measurement cues for face tracking. / Pnevmatikakis, Aristodemos; Stergiou, Andreas; Petsatodis, Theodoros et al.
2013 18th International Conference on Digital Signal Processing, DSP 2013. IEEE Press, 2013. s. 1-6 6622722 (International Conference on Digital Signal Processing proceedings).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Visual measurement cues for face tracking

AU - Pnevmatikakis, Aristodemos

AU - Stergiou, Andreas

AU - Petsatodis, Theodoros

AU - Katsarakis, Nikolaos

N1 - Conference code: 18

PY - 2013/12/6

Y1 - 2013/12/6

N2 - Particle filters allow for visual trackers with nonlinear measurements. In this paper we consider three different non-linear visual measurement cues, based on object detection, foreground segmentation and colour matching. Novel ways to obtain robust measurement likelihoods under a unified representation scheme are discussed, followed by a likelihood combination scheme for fusion. The resulting single and multi-cue particle filter trackers are compared in the scope of face tracking.

AB - Particle filters allow for visual trackers with nonlinear measurements. In this paper we consider three different non-linear visual measurement cues, based on object detection, foreground segmentation and colour matching. Novel ways to obtain robust measurement likelihoods under a unified representation scheme are discussed, followed by a likelihood combination scheme for fusion. The resulting single and multi-cue particle filter trackers are compared in the scope of face tracking.

KW - Face tracking

KW - Fusion

KW - Likelihood function

KW - Particle filters

KW - Visual measurements

U2 - 10.1109/ICDSP.2013.6622722

DO - 10.1109/ICDSP.2013.6622722

M3 - Article in proceeding

AN - SCOPUS:84888883802

SN - 978-146735805-7

T3 - International Conference on Digital Signal Processing proceedings

SP - 1

EP - 6

BT - 2013 18th International Conference on Digital Signal Processing, DSP 2013

PB - IEEE Press

T2 - International conference on Digital Signal Processing

Y2 - 1 July 2013 through 3 July 2013

ER -

Visual measurement cues for face tracking

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Citationsformater