| Abstract |
|
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that are computed from a training set using principal component analysis. Many complex image motions can be represented by a linear combination of a small number of these basis flows. The learned motion models may be used for optical flow estimation and for model-based recognition. For optical flow estimation we describe a robust, multi-resolution scheme for directly computing the parameters of the learned flow models from image derivatives. As examples we consider learning motion discontinuities, non-rigid motion of human mouths, and articulated human motion.
|
 Additional Information
|
Index Terms- Optical flow, learning, eigenspace methods, motion discontinuities, non-rigid and articulated motion.
Citation:
Michael J. Black, Yaser Yacoob, Allan D. Jepson, David J. Fleet,
"Learning Parameterized Models of Image Motion,"
cvpr,
p. 561,
1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97),
1997
|
