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

Computer Vision and Image Understanding Volume 113 Issue 12 Page 1210-1221 published_at 2009-12
アクセス数 : 910
ダウンロード数 : 178

今月のアクセス数 : 0
今月のダウンロード数 : 2
File
CVIU_113_1210.pdf 2.9 MB 種類 : fulltext
Title ( eng )
Representing images of a rotating object with cyclic permutation for view-based pose estimation
Creator
Tanaki Toru
Amano Toshiyuki
Source Title
Computer Vision and Image Understanding
Volume 113
Issue 12
Start Page 1210
End Page 1221
Abstract
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.
Keywords
view-based pose estimation
global appearance
cyclic group
column permutation matrix
block diagonalization
subspace methods
NDC
Electrical engineering [ 540 ]
Language
eng
Resource Type journal article
Publisher
Elsevier Inc.
Date of Issued 2009-12
Rights
Copyright (c) 2009 Elsevier Inc.
Publish Type Author’s Original
Access Rights open access
Source Identifier
[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