Multiple motion estimation using channel matrices

Authors:
Per-Erik Forssén;Hagen Spies
Affiliations:
Computer Vision Laboratory, Department of Electrical Engineering, Linköping University, Linköping, Sweden;R&D ContextVision AB, Linkööping, Sweden
Venue:
IWCM'04 Proceedings of the 1st international conference on Complex motion
Year:
2004

Citing 6
Cited 1

On the Fourier Properties of Discontinuous Motion

Journal of Mathematical Imaging and Vision
Signal Processing for Computer Vision

Signal Processing for Computer Vision
An Associative Perception-Action Structure Using a Localized Space Variant Information Representation

AFPAC '00 Proceedings of the Second International Workshop on Algebraic Frames for the Perception-Action Cycle
Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Optical flow estimation from monogenic phase

IWCM'04 Proceedings of the 1st international conference on Complex motion
Two-dimensional channel representation for multiple velocities

SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis

Optical flow estimation from monogenic phase

IWCM'04 Proceedings of the 1st international conference on Complex motion

Quantified Score

Hi-index	0.00

Visualization

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.