Dense discontinuous optical flow VIA contour-based segmentation

T. Amiaz*, N. Kiryati

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

19 Scopus citations

Abstract

We propose a new algorithm for dense optical flow computation. Dense optical flow schemes are challenged by the presence of motion discontinuities. In state of the art optical flow methods, over-smoothing of flow discontinuities accounts for most of the error. A breakthrough in the performance of optical flow computation has recently been achieved by Brox et al. Our algorithm embeds their functional within a contour-based segmentation framework. Piecewise-smooth flow fields are accommodated and flow boundaries are crisp. Experimental results show the superiority of our algorithm with respect to alternative techniques.

Original languageEnglish
Title of host publicationIEEE International Conference on Image Processing 2005, ICIP 2005
Pages1264-1267
Number of pages4
DOIs
StatePublished - 2005
EventIEEE International Conference on Image Processing 2005, ICIP 2005 - Genova, Italy
Duration: 11 Sep 200514 Sep 2005

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume3
ISSN (Print)1522-4880

Conference

ConferenceIEEE International Conference on Image Processing 2005, ICIP 2005
Country/TerritoryItaly
CityGenova
Period11/09/0514/09/05

Fingerprint

Dive into the research topics of 'Dense discontinuous optical flow VIA contour-based segmentation'. Together they form a unique fingerprint.

Cite this