@conference {18321, title = {Learning parameterized models of image motion}, booktitle = {Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on}, year = {1997}, month = {1997/06//}, pages = {561 - 567}, 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}, keywords = {image motion, Image sequences, learning, learning (artificial intelligence), model-based recognition, Motion estimation, multi-resolution scheme, non-rigid motion, optical flow, optical flow estimation, parameterized models, Principal component analysis, training set}, doi = {10.1109/CVPR.1997.609381}, author = {Black,M. J and Yacoob,Yaser and Jepson,A. D and Fleet,D. J} }