Representing images of a rotating object with cyclic permutation for view-based pose estimation

Tanaki Toru

Amano Toshiyuki

Kaneda Kazufumi

Computer Vision and Image Understanding

In this paper, we propose a novel approach using a cyclic group to model the appearance change in an image sequence of an object rotated about an arbitrary axis (1DOF out-of-plane rotation). In the sequence, an image xj is followed by an image xj+1. We represent the relationship between images by a cyclic group as xj+1 = Gxj , and obtain the matrix G by real block diagonalization. Then, G to the power of a real number is used to represent the image sequence and also for pose estimation. Two estimation methods are proposed and evaluated with real image sequences from the COIL-20, COIL-100, and ALOI datasets, and also compared to the Parametric Eigenspace method. Additionally, we discuss the relationship of the proposed approach to the pixel-wise Discrete Fourier Transform (DFT) and to linear regression, and also outline several extensions.

view-based pose estimation

global appearance

cyclic group

column permutation matrix

block diagonalization

subspace methods

Electrical engineering [ 540 ]

eng

Elsevier Inc.

Copyright (c) 2009 Elsevier Inc.

[ISSN] 1077-3142

[NCID] AA11028969

[DOI] 10.1016/j.cviu.2009.06.007

[DOI] http://dx.doi.org/10.1016/j.cviu.2009.06.007 isVersionOf