Multiple Motion Estimation using Channel Matrices

Per-Erik Forssén, Hagen Spies
IWCM04, Günzburg, Tyskland
International Workshop on Complex Motion (IWCM)
Volume LNCS 3417, Pages 54-65
October, 2006

Abstract

The motion field from image sequences of a dynamic 3D scene is in general piecewise continuous. Since two neighbouring regions may have completely different motions, motion estimation at the discontinuities is problematic. In particular spatial averaging of motion vectors is inappropriate at such positions. We avoid this problem by channel encoding brightness change constraint equations (BCCE) for each spatial position into a channel matrix. By spatial averaging of this channel representation and subsequently decoding we are able to estimate all significantly different motions occurring at the discontinuity, as well as their covariances. This paper extends and improves this multiple motion estimation scheme by locally selecting the appropriate scale for the spatial averaging.

Full Paper

Portable document format file PDF

Bibtex entry

@inproceedings{fs04b,
        Address = {G\"unzburg, Tyskland},
        Author = {Per-Erik Forss\'en and Hagen Spies},
        Booktitle = {International Workshop on Complex Motion (IWCM)},
        Date-Added = {2007-08-09 15:33:01 +0200},
        Date-Modified = {2007-08-09 15:34:01 +0200},
        Month = {October},
        Pages = {54--65},
        Title = {Multiple Motion Estimation using Channel Matrices},
        Volume = {LNCS 3417},
        Year = {2006}}