2D and 3D face localization for complex scenes

Ghassan Karame; Andreas Stergiou; Nikos Katsarakis; Panagiotis Papageorgiou; Aristodemos Pnevmatikakis

doi:10.1109/AVSS.2007.4425339

2D and 3D face localization for complex scenes

Ghassan Karame, Andreas Stergiou, Nikos Katsarakis, Panagiotis Papageorgiou, Aristodemos Pnevmatikakis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we address face tracking of multiple people in complex 3D scenes, using multiple calibrated and synchronized far-field recordings. We localize faces in every camera view and associate them across the different views. To cope with the complexity of 2D face localization introduced by the multitude of people and unconstrained face poses, a combination of stochastic and deterministic trackers, detectors and a Gaussian Mixture Model for face validation are utilized. Then faces of the same person seen from the different cameras are associated by first finding all possible associations and then choosing the best option by means of a 3D stochastic tracker. The performance of the proposed system is evaluated and is found enhanced compared to existing systems.

Original language	English
Title of host publication	2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings
Pages	371-376
Number of pages	6
DOIs	https://doi.org/10.1109/AVSS.2007.4425339
Publication status	Published - 2007
Event	2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 - London, United Kingdom Duration: 5 Sept 2007 → 7 Sept 2007

Other

Other	2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007
Country/Territory	United Kingdom
City	London
Period	5/09/07 → 7/09/07

Access to Document

10.1109/AVSS.2007.4425339

Cite this

@inproceedings{4b38de9c85e0468d8de759ae2fe432a8,

title = "2D and 3D face localization for complex scenes",

abstract = "In this paper, we address face tracking of multiple people in complex 3D scenes, using multiple calibrated and synchronized far-field recordings. We localize faces in every camera view and associate them across the different views. To cope with the complexity of 2D face localization introduced by the multitude of people and unconstrained face poses, a combination of stochastic and deterministic trackers, detectors and a Gaussian Mixture Model for face validation are utilized. Then faces of the same person seen from the different cameras are associated by first finding all possible associations and then choosing the best option by means of a 3D stochastic tracker. The performance of the proposed system is evaluated and is found enhanced compared to existing systems.",

author = "Ghassan Karame and Andreas Stergiou and Nikos Katsarakis and Panagiotis Papageorgiou and Aristodemos Pnevmatikakis",

year = "2007",

doi = "10.1109/AVSS.2007.4425339",

language = "English",

isbn = "9781424416967",

pages = "371--376",

booktitle = "2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings",

note = "2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 ; Conference date: 05-09-2007 Through 07-09-2007",

}

Karame, G, Stergiou, A, Katsarakis, N, Papageorgiou, P & Pnevmatikakis, A 2007, 2D and 3D face localization for complex scenes. in 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings., 4425339, pp. 371-376, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007, London, United Kingdom, 5/09/07. https://doi.org/10.1109/AVSS.2007.4425339

TY - GEN

T1 - 2D and 3D face localization for complex scenes

AU - Karame, Ghassan

AU - Stergiou, Andreas

AU - Katsarakis, Nikos

AU - Papageorgiou, Panagiotis

AU - Pnevmatikakis, Aristodemos

PY - 2007

Y1 - 2007

N2 - In this paper, we address face tracking of multiple people in complex 3D scenes, using multiple calibrated and synchronized far-field recordings. We localize faces in every camera view and associate them across the different views. To cope with the complexity of 2D face localization introduced by the multitude of people and unconstrained face poses, a combination of stochastic and deterministic trackers, detectors and a Gaussian Mixture Model for face validation are utilized. Then faces of the same person seen from the different cameras are associated by first finding all possible associations and then choosing the best option by means of a 3D stochastic tracker. The performance of the proposed system is evaluated and is found enhanced compared to existing systems.

AB - In this paper, we address face tracking of multiple people in complex 3D scenes, using multiple calibrated and synchronized far-field recordings. We localize faces in every camera view and associate them across the different views. To cope with the complexity of 2D face localization introduced by the multitude of people and unconstrained face poses, a combination of stochastic and deterministic trackers, detectors and a Gaussian Mixture Model for face validation are utilized. Then faces of the same person seen from the different cameras are associated by first finding all possible associations and then choosing the best option by means of a 3D stochastic tracker. The performance of the proposed system is evaluated and is found enhanced compared to existing systems.

UR - http://www.scopus.com/inward/record.url?scp=44849088397&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2007.4425339

DO - 10.1109/AVSS.2007.4425339

M3 - Conference contribution

AN - SCOPUS:44849088397

SN - 9781424416967

SP - 371

EP - 376

BT - 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings

T2 - 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007

Y2 - 5 September 2007 through 7 September 2007

ER -

2D and 3D face localization for complex scenes

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this