2026-03-08T17:04:15Z https://hiroshima.repo.nii.ac.jp/oai

oai:hiroshima.repo.nii.ac.jp:02001008 2025-02-18T03:07:34Z 1730444917621

Comparative study of path nomalizations for path prediction Shimomura, Yuji Harano, Tomotaka Tamaki, Toru Amano, Toshiyuki Kaneda, Kazufumi Uchida, Seiichi 540 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. http://purl.org/coar/resource_type/c_5794 Korea-Japan Joint Workshop on Frontiers of Computer Vision 2008-01 2008-01 AO 284 Proceedings of FCV 2008 289 284 The 14th Korea-Japan Joint Workshop on Frontiers of Computer Vision https://hiroshima.repo.nii.ac.jp/records/2001008 eng http://ir.lib.hiroshima-u.ac.jp/00021051 open access Copyright (c) 2008 Authors