Comparative study of path nomalizations for path prediction

Proceedings of FCV 2008 Page 284-289 published_at 2008-01
アクセス数 : 926
ダウンロード数 : 123

今月のアクセス数 : 1
今月のダウンロード数 : 0
File
FCV2008-Shinomura.pdf 1.4 MB 種類 : fulltext
Title ( eng )
Comparative study of path nomalizations for path prediction
Creator
Shimomura Yuji
Harano Tomotaka
Amano Toshiyuki
Uchida Seiichi
Source Title
Proceedings of FCV 2008
The 14th Korea-Japan Joint Workshop on Frontiers of Computer Vision
Start Page 284
End Page 289
Abstract
This paper disccusses two methods on normalization of a sample path for predicting paths of a pedestrian by using eigenspace. A path of a person is defined as a sequence of successive coordinates of the person over frames and represented the path as a vector with 2M elements of M number of coordinates. A problem of their prediction is that the method is based on subspace. To make a subspace from sample paths, all paths need to be normalized and resampled such that a path vector has the same number of elements. Because different sample paths have different number of frames. In this paper, we apply a normalization method using DP matching and discuss results of two predictions : resampling and DP.
NDC
Electrical engineering [ 540 ]
Language
eng
Resource Type conference paper
Publisher
Korea-Japan Joint Workshop on Frontiers of Computer Vision
Date of Issued 2008-01
Rights
Copyright (c) 2008 Authors
Publish Type Author’s Original
Access Rights open access
Date
[Created] 2008-01
Source Identifier
[URI] http://ir.lib.hiroshima-u.ac.jp/00021051