Presentation 2007-07-10
Improvement of Moving Object Extraction Based on Two-Layered Clustering of Affine Parameters
Takefumi KOJIMA, Satoshi INOUE, Kousuke IMAMURA, Hideo Hashimoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have shown a moving-object segmentation method that employs clustering of affine parameters for image blocks. The elements of affine parameters have different characteristic, so they have to be normalized for evaluating distance between them. In this paper, we propose a new method to solve those problems. This method, rejecting unreliable affine parameters in clustering and employing two-layered clustering, improves accuracy of moving-object extraction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Moving Object Extraction / Affine Parameters / Clustering
Paper # IE2007-30,MVE2007-33
Date of Issue

Conference Information
Committee MVE
Conference Date 2007/7/2(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improvement of Moving Object Extraction Based on Two-Layered Clustering of Affine Parameters
Sub Title (in English)
Keyword(1) Moving Object Extraction
Keyword(2) Affine Parameters
Keyword(3) Clustering
1st Author's Name Takefumi KOJIMA
1st Author's Affiliation Kanazawa University()
2nd Author's Name Satoshi INOUE
2nd Author's Affiliation Shiga Fujitsu Software Limited
3rd Author's Name Kousuke IMAMURA
3rd Author's Affiliation Kanazawa University
4th Author's Name Hideo Hashimoto
4th Author's Affiliation Kanazawa University
Date 2007-07-10
Paper # IE2007-30,MVE2007-33
Volume (vol) vol.107
Number (no) 130
Page pp.pp.-
#Pages 6
Date of Issue