Dense optical flow by iterative local window registration
Office Nat. d’Etudes et de Recherches Aerospatiales, Chatillon, France
In IEEE International Conference on Image Processing 2005 (2005), pp. I-137.
@conference{le2005dense,
title={Dense optical flow by iterative local window registration},
author={Le Besnerais, G. and Champagnat, F.},
booktitle={Image Processing, 2005. ICIP 2005. IEEE International Conference on},
volume={1},
isbn={0780391349},
year={2005},
organization={IEEE}
}
We study dense optical flow estimation using iterative registration of local window, also known as iterative Lucas-Kanade (LK) [B. Lucas et al, 1981]. We show that the usual iterative-warping scheme encounters divergence problems and propose a modified scheme with better behavior. It yields good results with a much lower cost than the exact dense LK algorithm, on simulated and real sequences.
January 10, 2011 by hgpu
