Presentation	2008-03-11 Detecting Incorrect Feafute Point Tracking by Affine Space Fitting Chika Takada, Yasuyuki Sugaya,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We present a new method for detecting incorrect feature point tracking. For 3-D reconstruction and motion segmentation, we track feature points through a video sequence, then remove outlier trajectories among them. If we detect image frames in which feature point tracking fails, we can correct incorrect trajectories and reuse them. In this paper, we detect incorrect feature point tracking by imposing the constraint that under the affine camera model feature trajectories should be in an affine space in the parameter space. Introducing a statistical model of image noise, we test the partial trajectories are sufficientlly reliable. Then we detect incorrect partial trajectories. Using real video images, we demonstrate that our proposed method sufficientlly detects incorrect feature point tracking.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	IE2007-313,PRMU2007-297
Date of Issue

Conference Information
Committee	IE
Conference Date	2008/3/3(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)	Detecting Incorrect Feafute Point Tracking by Affine Space Fitting
Sub Title (in English)
Keyword(1)
1st Author's Name	Chika Takada
1st Author's Affiliation	Department of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name	Yasuyuki Sugaya
2nd Author's Affiliation	Department of Information and Computer Sciences, Toyohashi University of Technology
Date	2008-03-11
Paper #	IE2007-313,PRMU2007-297
Volume (vol)	vol.107
Number (no)	538
Page	pp.pp.-
#Pages	8
Date of Issue