Video layer extraction and reconstruction

Abstract : The layer model describes images as the projection of a three dimensional scene composed of several opaque objects located at different depths from the camera. The background is the last layer, and the moving objects are projected upon it, in opposite order of their depth. When a layer is projected upon another, the one below is hidden, thus creating an occlusion. In the case of a video sequence, the layers move during the sequence and a layer might be hidden by another one during several images. In this article we present a variational method to extract layers from a video, recover the depth order and interpolate layers even in the case of total occlusion. The method is based on a known background. From a uniform motion hypothesis on the 3d objects, a deformation model of the projection on the image is deduced. A variational formulation is used to recover the model parameters, these allow the extraction of moving object layers, depth order and the reconstruction of the sequence
Type de document :
Communication dans un congrès
J. J. Villanueva. Visualization, Imaging, and Image Processing, Sep 2008, Palma, Spain. Acta Press, http://www.actapress.com/Abstract.aspx?paperId=33933, 2008, ISBN 978-0-88986-759-8
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00325422
Contributeur : Georges Koepfler <>
Soumis le : lundi 29 septembre 2008 - 11:40:43
Dernière modification le : mardi 11 octobre 2016 - 14:53:00

Identifiants

  • HAL Id : hal-00325422, version 1

Citation

Georges Koepfler, Sylvain Pelletier, Françoise Dibos. Video layer extraction and reconstruction. J. J. Villanueva. Visualization, Imaging, and Image Processing, Sep 2008, Palma, Spain. Acta Press, http://www.actapress.com/Abstract.aspx?paperId=33933, 2008, ISBN 978-0-88986-759-8. <hal-00325422>

Partager

Métriques

Consultations de la notice

53