Presentation 2000/12/8
Optical flow estimation by clustering of intersection group of constraint lines in a velocity space
Shunsuke HAYASHI, Hiroki IMAMURA, Yukiko KENMOCHI, Kazunori KOTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The current optical flow estimation method produced a large estimation error caused by a plural of movement of the objects in the image. This paper shows a new method of optical flow estimation using clustering algorithm for scatterd intersection group of constraint lines in a velocity spade. The clustering of intersection can separate and focused the regions of different movements, it can estimate well a optical flow especially for boundary of objects, complex movements and broad image conditions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) optical flow / constraint line / clustering / velocity space
Paper # CS2000-118,IE2000-128
Date of Issue

Conference Information
Committee CS
Conference Date 2000/12/8(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 Communication Systems (CS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Optical flow estimation by clustering of intersection group of constraint lines in a velocity space
Sub Title (in English)
Keyword(1) optical flow
Keyword(2) constraint line
Keyword(3) clustering
Keyword(4) velocity space
1st Author's Name Shunsuke HAYASHI
1st Author's Affiliation Graduate School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Hiroki IMAMURA
2nd Author's Affiliation Graduate School of Information Science, Japan Advanced Institute of Science and Technology
3rd Author's Name Yukiko KENMOCHI
3rd Author's Affiliation Graduate School of Information Science, Japan Advanced Institute of Science and Technology
4th Author's Name Kazunori KOTANI
4th Author's Affiliation Graduate School of Information Science, Japan Advanced Institute of Science and Technology
Date 2000/12/8
Paper # CS2000-118,IE2000-128
Volume (vol) vol.100
Number (no) 500
Page pp.pp.-
#Pages 6
Date of Issue