Robust modified L2 local optical flow estimation and feature tracking
Commun. Syst. Group, Tech. Univ. Berlin, Berlin, Germany
IEEE Workshop on Applications of Computer Vision (WACV), 2011
@inproceedings{senst2011robust,
title={Robust modified L2 local optical flow estimation and feature tracking},
author={Senst, T. and Eiselein, V. and Evangelio, R.H. and Sikora, T.},
booktitle={Applications of Computer Vision (WACV), 2011 IEEE Workshop on},
pages={685–690},
organization={IEEE},
year={2011}
}
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 L^2 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 (>25 fps) 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.
June 15, 2011 by hgpu
