direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Scientific Publications

Cross based Robust Local Optical Flow
Citation key 1448Senst2014
Author Tobias Senst and Thilo Borgmann and Ivo Keller and Thomas Sikora
Title of Book 21th IEEE International Conference on Image Processing
Pages 1967–1971
Year 2014
Address Paris,France
Month oct
Note ISBN: 978-1-4799-5750-7 DOI:10.1109/ICIP.2014.7025394
Abstract In many computer vision applications local optical flow methods are still a widely used. Such methods, like the Pyramidal Lucas Kanade and the Robust Local Optical Flow, have to address the trade–off between run time and accuracy. In this work we propose an extension to these methods that improves the accuracy especially at object boundaries. This extension makes use of the cross based variable support region generation proposed in Zhang2009 accounting for local intensity discontinuities. In the evaluation using Middlebury data set we prove the ability of the proposed extension to increase the accuracy by a slight increase of run time.
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe