Presentation	1998/1/23 Study of Estimating Optical Flow Using Kalman Filter Masahide Matsunaga, Yukio Kaneda, Toshio Ito,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Optical flow is an important information for estimating motion parameters and 3D structure. Generally, optical flow is estimated by gradient method. In the previous method, we can estimate optical flow from only two images. In this paper we suppose that optical flow varies gradually as time passes. And we propose to use kalman filter for estimating more correct optical flow from sequential images. From the experimental results, the effectiveness of proposed methods have confirmed.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Optical Flow / Gradient Method / Kalman Filter
Paper #	PRMU97-209
Date of Issue

Conference Information
Committee	PRMU
Conference Date	1998/1/23(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	Pattern Recognition and Media Understanding (PRMU)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Study of Estimating Optical Flow Using Kalman Filter
Sub Title (in English)
Keyword(1)	Optical Flow
Keyword(2)	Gradient Method
Keyword(3)	Kalman Filter
1st Author's Name	Masahide Matsunaga
1st Author's Affiliation	Graduate School of Science and Technology, Kobe University()
2nd Author's Name	Yukio Kaneda
2nd Author's Affiliation	Graduate School of Science and Technology, Kobe University
3rd Author's Name	Toshio Ito
3rd Author's Affiliation	Electronics Engineering Div., Daihatsu Motor Co.
Date	1998/1/23
Paper #	PRMU97-209
Volume (vol)	vol.97
Number (no)	501
Page	pp.pp.-
#Pages	6
Date of Issue