Conference/ProceedingsProceedings of the 17th IEEE International Conference on Image Processing (ICIP 2010)
Start date26.09.2010
End date29.09.2010
AddressHong Kong
Author(s)Michael Tok, Alexander Glantz, Marina Georgia Arvanitidou, Andreas Krutz, Thomas Sikora
TitleCompressed Domain Global Motion Estimation using the Helmholtz Tradeoff Estimator
AbstractSeveral algorithms for global motion estimation in video sequences using pixel- or block-based approaches have been published.
Most known pixel-based methods lack in performance while when using block-based algorithms working on motion vectors, robustness to outliers and accuracy is missing.
In this paper we present the fundamentals of a significantly improved, robust block-based method for global motion estimation in compressed
domain following the generic Helmholtz principle. To this aim, we use motion vector fields as provided by MPEG data streams.
Background PSNR values for four motion compensated test sequences show that our new method delivers results comparable to more complex algorithms.
Key wordscompression, global motion estimation, helmholtz tradeoff estimator, compressed domain, robust regression
NoteISBN: 978-1-4244-7993-1
ISSN: 1522-4880