Animal gaits from video : comparative studies

Laurent Favreau 1 Lionel Reveret 1 Christine Depraz 1 Marie-Paule Cani 1
1 EVASION - Virtual environments for animation and image synthesis of natural objects
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We present a method for animating 3D models of animals from existing live video sequences such as wild life documentaries. Videos are first segmented into binary images on which principal component analysis (PCA) is applied. The time-varying coordinates of the images in the PCA space are then used to generate 3D animation. This is done through interpolation with radial basis functions of 3D pose examples associated with a small set of keyimages extracted from the video. In addition to this processing pipeline, our main contributions are: an automatic method for selecting the best set of key-images for which the designer will need to provide 3D pose examples, and a simple algorithm based on PCA images to resolve 3D pose prediction ambiguities. These ambiguities are inherent to many animal gaits when only monocular view is available.
Type de document :
Article dans une revue
Graphical Models, Elsevier, 2006, 68 (2), pp.212-234
Liste complète des métadonnées
Contributeur : Lionel Reveret <>
Soumis le : mardi 26 juin 2012 - 11:15:07
Dernière modification le : mercredi 11 avril 2018 - 01:56:09
Document(s) archivé(s) le : jeudi 27 septembre 2012 - 02:20:30


  • HAL Id : inria-00384231, version 1




Laurent Favreau, Lionel Reveret, Christine Depraz, Marie-Paule Cani. Animal gaits from video : comparative studies. Graphical Models, Elsevier, 2006, 68 (2), pp.212-234. 〈inria-00384231〉



Consultations de la notice


Téléchargements de fichiers