conference paper

Conference/ProceedingsIEEE 10th International Workshop on Multimedia Signal Processing, MMSP 8-10 October 2008, Proceedings, Cairns, Australia
Start date08.10.2008
End date10.10.2008
OrganisationIEEE MMSP
EditorDavid Feng, Thomas Sikora, W. C. Siu, Jian Zhang, Ling Guan, Jean Luc Dugelay, Qiang Wu, Wanqing Li
VolumeOctober 2008
Author(s)Lutz Goldmann, Antonio Rama, Thomas Sikora, Francesc Tarres
TitleOn the Detection and Localization of Facial Occlusions and its Use within Different Scenarios
AbstractIn recent years advanced video codecs have been developed, such as standardized in MPEG-4. The latest video codec H.264/AVC provides compression performance superior to previous standards, but is based on the same basic motioncompensated-DCT architecture. However, for certain types of video, it has been shown that it is possible to outperform the H.264/AVC using an object-based video codec. Towards a general-purpose object-based video coding system we present an automated approach to separate a video sequences into subsequences regarding its camera motion type. Then, the subsequences are coded either with an object-based codec or the common H.264/AVC. Applying different video codecs for different kinds of camera motion, we achieve a higher overall coding gain for the video sequence. In first experimental evaluations, we demonstrate the excellence performance of this approach on two test sequences.
Key wordsface detection, face analysis, classification module, occlusion, H.264/AVC, object-based video codec
NoteISBN 978-1-4244-2295-1