Presentation	2012/11/29 Improvement in Moving Object Segmentation Method Using X-means Clustering Considering Temporal Correlation Between Motion Information KOUSUKE IMAMURA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	The authors have proposed a moving object segmentation method based on x-means clustering and region segmentation. In this paper, I propose an improvement strategy utilizing temporal correlation between motion information in the moving object segmentation method using x-means clustering. X-means clustering applies to motion information between three frames, and it is estimated whether a feature point is in uncovered background or occlusion from temporal difference of the clustering result at the each feature point. The appropriate labeling to the regions provides the improvement of the moving object segmentation results. In addition, I improve the credibility decision of motion information at the feature point. Experimental results show that the proposed method provides segmentation results with the suitable object number.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	Vol.2012-AVM-79
Date of Issue

Conference Information
Committee	IE
Conference Date	2012/11/29(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	Image Engineering (IE)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Improvement in Moving Object Segmentation Method Using X-means Clustering Considering Temporal Correlation Between Motion Information
Sub Title (in English)
Keyword(1)
1st Author's Name	KOUSUKE IMAMURA
1st Author's Affiliation	()
Date	2012/11/29
Paper #	Vol.2012-AVM-79
Volume (vol)	vol.112
Number (no)	335
Page	pp.pp.-
#Pages	6
Date of Issue