Presentation 1994/1/21
Optical flow Constraint Using Affine Transform
Tomoyuki Fujitomi, Noboru Ohnishi, Noboru Sugie,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is a important research field in computer vision to extract optical flow form sequential images,and many algorithms have been proposed.Especially the gradient method that Horn proposed has the advantage of being able to extract optical flow only by numeraical calculation.However in the constranit of the gradient method,only parallel translation is considered.We introduce the affine transform so as to obtain constraint consdering rotate and scale change tranforms.Experimental results show the validity of this method by use of synthesized images.And we discuss about extracting optical flow in a case of occuring parallel,scale change and rotate transforms simultaneously
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Affine transform / optical flow constraint / Gradient method / Virtual intensity / Line pattern
Paper # PRU93-116
Date of Issue

Conference Information
Committee PRU
Conference Date 1994/1/21(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 Understanding (PRU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Optical flow Constraint Using Affine Transform
Sub Title (in English)
Keyword(1) Affine transform
Keyword(2) optical flow constraint
Keyword(3) Gradient method
Keyword(4) Virtual intensity
Keyword(5) Line pattern
1st Author's Name Tomoyuki Fujitomi
1st Author's Affiliation Graduate School of System Engineering,Kobe University()
2nd Author's Name Noboru Ohnishi
2nd Author's Affiliation Electronics Engineering Div System Planning Office,Daihatsu Motor Co.,Ltd.
3rd Author's Name Noboru Sugie
3rd Author's Affiliation Division of Intelligence Science,Graduate School of Science and Technology,Kobe Univerisity
Date 1994/1/21
Paper # PRU93-116
Volume (vol) vol.93
Number (no) 431
Page pp.pp.-
#Pages 8
Date of Issue