Fast modified Horn & Schunck method for the estimation of optical flow fields

Author

Baarir, Z.-E. ; Charif, F.

Author_Institution

Electron. Dept., Univ. of Biskra, Biskra, Algeria

fYear

2011

fDate

4-7 Oct. 2011

Firstpage

283

Lastpage

288

Abstract

This paper presents a fast, accurate and reliable modified Horn & Schunck approach for robust boundary preserving estimation of optical flow where only 30 iterations are used. The proposed method is derived from the benchmark algorithm of Horn & Schunck and Simoncelli´s matched-pair 5 tap filters, such that it produces robust, fast and exact detection of motion boundaries and it is very simple to implement. Experimental results using synthetic and real optical flows are presented to demonstrate the effectiveness of our method in comparison to selected methods.

Keywords

estimation theory; filtering theory; image motion analysis; image sequences; Horn & Schunck method; Simoncelli´s matched-pair 5 tap filters; benchmark algorithm; exact detection; motion boundary; optical flow fields estimation; real optical flow; robust boundary preserving estimation; synthetic optical flow; Adaptive optics; Computer vision; Image motion analysis; Image sequences; Matched filters; Optical filters; Optical imaging; Horn & Schunck algorithm; Simoncelli´s filters; optical flow estimation; synthetic and real image sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Systems (SiPS), 2011 IEEE Workshop on

Conference_Location

Beirut

ISSN

2162-3562

Print_ISBN

978-1-4577-1920-2

Type

conf

DOI

10.1109/SiPS.2011.6088990

Filename

6088990