Presentation 2008-03-22
Estimating Unobserved Motion of a Spherical Object by Acquiring its Model from Image Sequence
Naoki OKADA, Tomohiro YABUUCHI, Takuya FUNATOMI, Koh KAKUSHO, Michihiko MINOH,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In conventional methods of object tracking, the position and posture of the object are estimated from their appearances in the image. However, those appearances cannot be obtained when the object is occluded by others. Moreover, the appearances that directly describe the posture of a spherical object like a ball cannot be obtained as image features though it is often tracked in a sportscast. Object's motion is the physical phenomenon in which object's states including its position and posture change from moment to moment. Although the position and the posture of an object have independent degrees of freedom, they influence with each other when the object is in move. Using this relation, it is possible to estimate one of them from the other. In this article, we introduce a model of object motion, which describes how the position and posture change with respect to time by physical laws of motion for estimating the position or posture invisible in the image sequence from visible ones.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) motion estimation / physical laws of motion / spherical object
Paper # MVE2007-81
Date of Issue

Conference Information
Committee MVE
Conference Date 2008/3/15(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) Estimating Unobserved Motion of a Spherical Object by Acquiring its Model from Image Sequence
Sub Title (in English)
Keyword(1) motion estimation
Keyword(2) physical laws of motion
Keyword(3) spherical object
1st Author's Name Naoki OKADA
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name Tomohiro YABUUCHI
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
3rd Author's Name Takuya FUNATOMI
3rd Author's Affiliation ACCMS, Kyoto University
4th Author's Name Koh KAKUSHO
4th Author's Affiliation ACCMS, Kyoto University
5th Author's Name Michihiko MINOH
5th Author's Affiliation ACCMS, Kyoto University
Date 2008-03-22
Paper # MVE2007-81
Volume (vol) vol.107
Number (no) 554
Page pp.pp.-
#Pages 6
Date of Issue