Two-dimensional channel representation for multiple velocities

Authors:
Hagen Spies;Per-Erik Forssén
Affiliations:
Computer Vision Laboratory, Dept. of Electrical Engineering, Linköping University, Linköping, Sweden and ContextVision AB, Linköping, Sweden;Computer Vision Laboratory, Dept. of Electrical Engineering, Linköping University, Linköping, Sweden
Venue:
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Year:
2003

Citing 2
Cited 1

On the Fourier Properties of Discontinuous Motion

Journal of Mathematical Imaging and 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

Multiple motion estimation using channel matrices

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a two-dimensional information representation, where small but overlapping Gaussian kernels are used to encode the data in a matrix. Apart from points we apply this to constraints that restrict the solution to a linear subspace. A localised decoding scheme accurately extracts multiple solutions together with an estimate of the covariances. We employ the method in optical flow computations to determine multiple velocities occurring at motion discontinuities.