![MCG](../MCG_logo.gif) |
A Multiresolution Model-based Segmentation
Algorithm for 3-D Motion and Structure Estimation
W.B. Goh & G.R.
Martin.
Proceedings of IEEE TENCON'94,
Singapore, August 1994, pp 862-866.
Abstract:
It became apparent, even in the early works of Schunck
that the task of optical flow estimation has to be carried out in conjunction
with the task of motion segmentation (i.e. motion boundary detection).
This fact has motivated the development of a novel model-based algorithm
which is able to segment the optical flow field in an image into homogeneous
regions which are consistent with a linear affine flow model. Furthermore,
to ensure robustness in the presence of noise, this region-growing process
is implemented within the hierarchical framework of a spatial lowpass pyramid.
The results of applying this algorithm to the problem of estimating 3-D
motion and structure in monocular image sequences are presented.
|