Analysis of Contour Motions
Ce Liu, William T. Freeman & Edward H. Adelson
Presented at Advances in Neural Information Processing Systems
(NIPS) 2006
Received the Best Student Paper Award [pdf][ppt]
What
A contour-based motion analysis system is proposed to infer contour grouping
as well as the motion along the contour for textureless objects under
occlusion.
Why
A reliable motion estimation algorithm must function under a wide range
of conditions. One regime, which we consider here, is the case of moving
objects with contours but no visible texture. Tracking distinctive features
such as corners can disambiguate the motion of contours, but spurious
features such as T-junctions can be badly misleading. It is difficult
to determine the reliability of motion from local measurements, since
a full rank covariance matrix can result from both real and spurious features.
How
We propose a novel approach that avoids these points altogether, and
derives global motion estimates by utilizing information from three levels
of contour analysis: edgelets, boundary fragments and contours [1]. Boundary
fragment are chains of orientated edgelets, for which we derive motion
estimates from local evidence. The uncertainties of the local estimates
are disambiguated after the boundary fragments are properly grouped into
contours. The grouping is done by constructing a graphical model and marginalizing
it using rejection sampling. We propose two equivalent representations
in this graphical model, reversible switch variables attached to the ends
of fragments and fragment chains, to capture both local and global statistics
of boundaries. Our system is successfully applied to both synthetic and
real video sequences containing high-contrast boundaries and textureless
regions. The system produces good motion estimates along with properly
grouped and completed contours.
Results
References
[1] Ce Liu, William T. Freeman and Edward H. Adelson. Analysis of Contour
Motions. Advances in Neural Information Processing Systems (NIPS), 2006.
|