Applies mean field technique and presents a deterministic algorithm to determine the optical flow and motion boundaries. To deal with the problem of large motion, the authors present an adaptive multigrid approach, which also greatly reduces the computation time. This algorithm is fully parallelizable and iterative. The performance of the proposed method is compared against known algorithms using performance measures proposed by Barren et al. [1992]. Experimental results indicate that the present approach provides good estimates of optical flow and motion boundaries.<>
Motion segmentation and estimation
Proceedings of 1st International Conference on Image Processing ; 2 ; 785-789 vol.2
1994-01-01
482785 byte
Conference paper
Electronic Resource
English
Motion estimation and segmentation
British Library Online Contents | 1996
|Motion Segmentation and Estimation
British Library Conference Proceedings | 1994
|Joint estimation of segmentation and structure from motion
British Library Online Contents | 2013
|Hierarchical Estimation and Segmentation of Dense Motion Fields
British Library Online Contents | 2002
|