 |
 |
|
|
| Detailed view | Conference proceedings |
 |
| CARI'10 - 10th African Conference on Research in Computer Science and Applied Mathematics, Yamoussoukro : Côte D'Ivoire (2010) |
|
|
| Attached file list to this document: | ||||||||||
|
||||||||||
|
|
|
| A new approach for regularization of inverse problems in images processing |
|
|
| Innocent Souopgui1Emmanuel Kamgnia2François-Xavier Le Dimet1Arthur Vidard1 |
|
|
|
| Optical flow motion estimation from two images is limited by the aperture problem. A method to deal with this problem is to use regularization techniques. Usually, one adds a regularization term with appriopriate weighting parameter to the optical flow cost funtion. Here, we suggest a new approach to regularization for optical flow motion estimation. In this approach, all the regularization informations are used in the definition of an appropriate norm for the cost function via a trust function to be defined, one does not ever need weighting parameter. A simple derivation of such a trust function from images is proposed and a comparison with usual approaches is presented. These results show the superiority of such approach over usual ones. |
|
|
|
|
|
|
|
|
|
| 1: | INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann - MOISE |
|
|
| 2: | UYI - Université de Yaoundé I |
|
|
|
|
|
|
|
| Motion estimation – Optical flow – Image – Regularization |
| hal-00539635, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00539635 | |
| oai:hal.archives-ouvertes.fr:hal-00539635 | |
| From: Innocent Souopgui | |
| Submitted on: Wednesday, 24 November 2010 18:07:53 | |
| Updated on: Wednesday, 27 February 2013 11:59:22 | |
