Presentation 2010-05-14
Memory Reduction Method Using Subspaces of Local Features for 3D Object Recognition
Takahiro KASHIWAGI, Takumi TOYAMA, Koichi KISE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recognition methods for 3D objects using local features of their 2D images have been proposed. A drawback of these methods is that a huge amount of memory is required to store a lot of local features in a database. In this report, we propose a memory reduction method by using subspaces that are spanned by local features extracted from the same part of the object in different poses. The proposed method is successful to reduce the memory down to about 1/18 of the memory for storing all local features, while it is capable of keeping the recognition rate of 98.9%. Since the subspaces are with the information of poses of objects, the proposed method is capable of estimating the pose of the object in the query image.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Subspace method / Memory reduction / Local feature / 3D object recognition
Paper # IE2010-31,PRMU2010-19,MI2010-19
Date of Issue

Conference Information
Committee MI
Conference Date 2010/5/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Medical Imaging (MI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Memory Reduction Method Using Subspaces of Local Features for 3D Object Recognition
Sub Title (in English)
Keyword(1) Subspace method
Keyword(2) Memory reduction
Keyword(3) Local feature
Keyword(4) 3D object recognition
1st Author's Name Takahiro KASHIWAGI
1st Author's Affiliation Graduate School of Engineering, Osaka Prefecture University()
2nd Author's Name Takumi TOYAMA
2nd Author's Affiliation Graduate School of Engineering, Osaka Prefecture University
3rd Author's Name Koichi KISE
3rd Author's Affiliation Graduate School of Engineering, Osaka Prefecture University
Date 2010-05-14
Paper # IE2010-31,PRMU2010-19,MI2010-19
Volume (vol) vol.110
Number (no) 28
Page pp.pp.-
#Pages 6
Date of Issue