Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Identity recognition-based correction mechanism for face tracking

 
: Stasiak, L.; Vicente-Garcia, R.

:

Perales Lopez, F.J.:
Articulated motion and deformable objects. 6th international conference, AMDO 2010 : Port d'Andratx, Mallorca, Spain, July 7-9, 2010; Proceedings
Berlin: Springer, 2010 (Lecture Notes in Computer Science 6169)
ISBN: 978-3-642-14060-0
ISBN: 3-642-14060-2
ISSN: 0302-9743
S.203-212
International Conference on Articulated Motion and Deformable Objects (AMDO) <6, 2010, Port d'Andratx>
Englisch
Konferenzbeitrag
Fraunhofer IPK ()
face tracking; biometric; face recognition; particle-filtering

Abstract
A system for parallel face detection, tracking and recognition in real-time video sequences is being developed. The particle filtering is utilized for the purpose of combined and effective detection, tracking and recognition. Temporal information contained in videos is utilized. Fast, skin color-based face extraction and normalization technique is applied. Consequently, real-time processing is achieved. Implementation of face recognition mechanisms within the tracking frame- work is used not only for the purpose of identity recognition, but also to improve the tracking robustness in case of multi-person tracking scenarios. In such scenarios, face-to-track assignment conflicts can often be resolved with the use of motion modeling. However, in case of close trajectories, motio n-based conflict resolution can be erroneous. Identity clue can be used to improve tracking quality in such cases. This paper describes the concept of face tracking corrections with the use of identity recognition mechanism, implemented within a compact particle filtering-based framework for face detection, tracking and recog- nition.

: http://publica.fraunhofer.de/dokumente/N-154363.html