A Model of Binocular Gaze Estimation

Miles Hansard 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Binocular image-pairs contain information about the three-dimensional structure of the visible scene, which can be recovered by the identification of corresponding points. However, the resulting disparity field also depends on the orientation of the eyes. If it is assumed that the exact eye-positions cannot be obtained from oculomotor feedback, then the gaze parameters must also be recovered from the images, in order to properly interpret the retinal disparity field. Existing models of biological stereopsis have addressed this issue independently of the binocularcorrespondence problem. It has been correctly assumed that if the correspondence problem can be solved, then the disparity field can be decomposed into gaze and structure components, as described above. In this work we take a different approach; we emphasize that although the complete point-wise disparity field is sufficient for gaze estimation, it is not in fact necessary. We show that the gaze parameters can be recovered directly from the images, independently of the point-wise correspondences.
Type de document :
Poster
COSYNE 2007 - 4th Computational and Systems Neuroscience Meeting, Feb 2007, Salt Lake City, United States. 2007, 〈http://www.cosyne.org/c/images/b/b3/Cosyne-poster-I-49.pdf〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00590233
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:47:25
Dernière modification le : mercredi 11 avril 2018 - 01:58:43
Document(s) archivé(s) le : jeudi 4 août 2011 - 03:07:28

Identifiants

  • HAL Id : inria-00590233, version 1

Collections

Citation

Miles Hansard, Radu Horaud. A Model of Binocular Gaze Estimation. COSYNE 2007 - 4th Computational and Systems Neuroscience Meeting, Feb 2007, Salt Lake City, United States. 2007, 〈http://www.cosyne.org/c/images/b/b3/Cosyne-poster-I-49.pdf〉. 〈inria-00590233〉

Partager

Métriques

Consultations de la notice

364

Téléchargements de fichiers

167