Communication science et technologie
Volume 13, Numéro 1, Pages 49-67
2015-01-01
Auteurs : Mokhtaria Barnoussi . Abdelhamid Loukil . Lahouari Kaddour .
Abstract — Accurate and real-time camera pose estimation is an important issue for applications such as Augmented Reality (AR), SLAMs (Simultaneous Localization and Mapping) in mobile robotics or even Intelligent Video Surveillance (IVS). The presented work concerns the implementation and experimentation of an automatic and real-time pose estimation of camera that will be part of an augmented reality system. The camera pose is estimated thanks to the permanent presence, in the filmed scene, of a marker (coded target) whose position and 3D geometry are perfectly known. In order to reduce the computation time and avoid marker tracking failure, we proposed our own marker. This allowed us to make an accurate alignment and real-time 3D synthetic objects in the real scene.
Keywords — Augmented reality / camera calibration / pose estimation / tracking / coded marker.
Bentazi Fettouma
.
pages 63-68.
Tadrist R.
.
Maamoun M.
.
Hassani A.
.
Kebli I.
.
Nesba A.
.
pages 611-622.
Ajgou R
.
Sbaa S
.
Aouragh S
.
Taleb Ahmed
.
pages 21-26.
Boudihir Med Elarbi
.
Khelfi S.
.
Benmohamed M.
.
Rahmoun A.
.
pages 60-68.