Presentation 1999/12/17
Estimating Optical Flow by Interpolated Quadratic Surfaces Matching
Ben-yao WU, Sosuke TSUKAMOTO, Kazutoshi KOGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Many of approaches to estimate velocity field (optical flow) from sequential images have been proposed since 70's. The gradient-based method and the correlation-based method are typically used. We use both of them by interpolating quadratic surfaces of intensity in the vicinity of each pixel on successive frames. Under the rigidness assumption, we can match the brightness and its gradient distribution of a local region on each frame, and then the local velocity vector can be obtained. Experimental results shown here are comfirmed the performance of presented method for several synthetic and real images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) optical flow / computer vision / velocity field / smoothness constraint / curved surface
Paper # PRMU99-188
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/12/17(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) Estimating Optical Flow by Interpolated Quadratic Surfaces Matching
Sub Title (in English)
Keyword(1) optical flow
Keyword(2) computer vision
Keyword(3) velocity field
Keyword(4) smoothness constraint
Keyword(5) curved surface
1st Author's Name Ben-yao WU
1st Author's Affiliation Faculty of Engineering, Yamaguchi University()
2nd Author's Name Sosuke TSUKAMOTO
2nd Author's Affiliation Faculty of Engineering, Yamaguchi University
3rd Author's Name Kazutoshi KOGA
3rd Author's Affiliation Faculty of Education, Yamaguchi University
Date 1999/12/17
Paper # PRMU99-188
Volume (vol) vol.99
Number (no) 515
Page pp.pp.-
#Pages 8
Date of Issue