Learning parameterized models of image motion

TitleLearning parameterized models of image motion
Publication TypeConference Papers
Year of Publication1997
AuthorsBlack MJ, Yacoob Y, Jepson AD, Fleet DJ
Conference NameComputer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Date Published1997/06//
Keywordsimage 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

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