Higher Dimensional Affine Registration and Vision Applications

Abstract. Affine registration has a long and venerable history in computer vision literature, and extensive work have been done for affine registrations in IR2 and IR3 . In this paper, we study affine registrations in IRm for m > 3, and to justify breaking this dimension barrier, we show two interesting types of matching problems that can be formulated and solved as affine registration problems in dimensions higher than three: stereo correspondence under motion and image set matching. More specifically, for an object undergoing non-rigid motion that can be linearly modelled using a small number of shape basis vectors, the stereo correspondence problem can be solved by affine registering points in IR3n . And given two collections of images related by an unknown linear transformation of the image space, the correspondences between images in the two collections can be recovered by solving an affine registration problem in IRm , where m is the dimension of a PCA subspace. The algorithm ...

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Yu-Tseh Chi, S. M. Nejhum Shahed, Jeffrey Ho, Ming-Hsuan Yang
• Keywords: Affine Registering Points, Affine Registration Algorithm, Affine Registration Problems, Affine Registrations, Computer Vision, ECCV 2008, Exact Affine Transformation