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.
Dense optical flow by iterative local window registration
2005-01-01
222630 byte
Conference paper
Electronic Resource
English
Dense Optical Flowby Iterative Local Window Registration
British Library Conference Proceedings | 2005
|Image Registration, Optical Flow and Local Rigidity
British Library Online Contents | 2001
|Dense Structure from a Dense Optical Flow Sequence
British Library Online Contents | 1998
|Dense Structure from a Dense Optical Flow Sequence
British Library Conference Proceedings | 1995
|An Iterative Algorithm for Shape Registration
British Library Conference Proceedings | 1994
|