Enhancement of the Horn and Schunck optic flow algorithm by means of median filters

Author

Bartolini, Franco ; Piva, Alessaiidro

Author_Institution

Dipt. di Ingegneria Elettronica, Firenze Univ., Italy

Volume

2

fYear

1997

fDate

2-4 Jul 1997

Firstpage

503

Abstract

For optic flow computation the Horn and Schunck (1980) algorithm is one of the most used and powerful. Some drawbacks are, nevertheless, intrinsically related to the approach that it used. A smoothness constraint is imposed to the flow field in order to produce a solution. This constraint causes the estimated field to be incorrect where motion discontinuities are present. The weight of this smoothness constraint is reduced by using median filters. Motion boundaries are better preserved by the modified algorithm. Results are presented and possible developments are proposed

Keywords

image segmentation; median filters; motion estimation; smoothing methods; Horn and Schunck optic flow algorithm; estimated field; flow field; median filters; modified algorithm; motion boundaries; motion discontinuities; smoothness constraint; Electronic mail; Equations; Image motion analysis; Motion estimation; Nonlinear optics; Optical computing; Optical devices; Optical filters; Pixel; Video coding;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on

Conference_Location

Santorini

Print_ISBN

0-7803-4137-6

Type

conf

DOI

10.1109/ICDSP.1997.628385

Filename

628385