3D Motion Estimation using Expansion Matching and KL based Canonical Images

This paper describes a novel approach to 3D motion estimation of planar objects based on eigennormalization, Expansion Matching (EXM) and a scaled orthographic projection model. Our approach leads to a comprehensive temporal description of all degrees of freedom in 3D (3 rotations and 3 translations). The 3D motion parameters of the objects are approximated by the corresponding a ne parameters. The objects in each frame of a video sequence are normalized to a set of canonical images using principal component normalization procedure. The normalization approach here is based on principal components of the intensity weighted spatial values and not on the intensity values as in works such as eigenfaces. The canonical images generated di er only in orientation. Expansion Matching (EXM) is then used to nd the di erences in orientation. A ne transformations between the shapes also are derived. The pose of the shape in 3D space can therefore be estimated. Experiments on video sequences of pla...

• Type: Conference
• Year: 1998
• Where: ICIP
• Authors: Zhiqian Wang, Jezekiel Ben-Arie
• Keywords: ICIP 1998, Image Processing, Planar Objects, Principal Component Normalization, Real 3D Rotations