Conference/ProceedingsIEEE Workshop on Motion and Video Computing (WMVC)
Start date05.01.2011
End date07.01.2011
AddressKona, USA
EditorEric Mortensen
Author(s)Tobias Senst, Volker Eiselein, Rubén Heras Evangelio, Thomas Sikora
TitleRobust Modified L2 Local Optical Flow Estimation and Feature Tracking
AbstractThis 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.
Key wordsmultimedia analysis, feature tracking, robust estimation, optical flow,RLOFLib
NoteIEEE Catalog Number: CFP11082-CDR
ISBN: 978-1-4244-9495-8
DOI: 10.1109/WACV.2011.5711571