direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Scientific Publications

Robust Modified L2 Local Optical Flow Estimation and Feature Tracking
Citation key 1277Senst2011
Author Tobias Senst and Volker Eiselein and Rubén Heras Evangelio and Thomas Sikora
Title of Book IEEE Workshop on Motion and Video Computing (WMVC)
Pages 685–690
Year 2011
Address Kona, USA
Month jan
Note IEEE Catalog Number: CFP11082-CDR ISBN: 978-1-4244-9495-8 DOI: 10.1109/WACV.2011.5711571
Editor Eric Mortensen
Abstract This paper describes a robust method for the local optical flow estimation and the KLT feature tracking performed on the GPU. Therefore we present an estimator based on the L2 norm with robust characteristics. In order to increase the robustness at discontinuities we propose a strategy to adapt the used region size. The GPU implementation of our approach achieves real-time (>25fps) performance for High Definition (HD) video sequences while tracking several thousands of points. The benefit of the suggested enhancement is illustrated on the Middlebury optical flow benchmark.
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions