Motion estimation with object based regularisation |
| |
| Authors: | Panis S. Cosmas J.P. |
| |
| Affiliation: | Dept. of Electron. Eng., Queen Mary & Westfield Coll., London; |
| |
| Abstract: | A dynamic programming based matching method for motion estimation. That optimises a Bayesian maximum likelihood function in a 3-D optimisation space, is presented. The Bayesian function consists of a matching cost and an object based 2-D regularisation cost. The method gives results more accurate than block-based matching since the motion boundaries are close to the actual object boundaries |
| |
| Keywords: | |
|
|
