Coherent Laplacian 3-D Protrusion Segmentation

Fabio Cuzzolin 1 Diana Mateus 1 David Knossow 1 Edmond Boyer 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 : In this paper, an analysis of locally linear embedding (LLE) in the context of clustering is developed. As LLE conserves the local affine coordinates of points, shape protrusions as high-curvature regions of the surface are preserved. Also, LLE's covariance constraint acts as a force stretching those protrusions and making them wider separated and lower dimensional. A novel scheme for unsupervised body-part segmentation along time sequences is thus proposed in which 3-D shapes are clustered after embedding. Clusters are propagated in time, and merged or split in an unsupervised fashion to accommodate changes of the body topology. Comparisons on synthetic, and real data with ground truth, are run with direct segmentation in 3-D by EM clustering and ISOMAP-based clustering. Robustness and the effects of topology transitions are discussed.
Type de document :
Communication dans un congrès
CVPR 2008 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2008, Anchorage, United States. IEEE Computer Society, pp.1-8, 2008, 〈10.1109/CVPR.2008.4587452〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00590250
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:49:47
Dernière modification le : mercredi 11 avril 2018 - 01:59:05
Document(s) archivé(s) le : vendredi 9 novembre 2012 - 10:22:12

Fichiers

CuzzolinCVPR08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Fabio Cuzzolin, Diana Mateus, David Knossow, Edmond Boyer, Radu Horaud. Coherent Laplacian 3-D Protrusion Segmentation. CVPR 2008 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2008, Anchorage, United States. IEEE Computer Society, pp.1-8, 2008, 〈10.1109/CVPR.2008.4587452〉. 〈inria-00590250〉

Partager

Métriques

Consultations de la notice

436

Téléchargements de fichiers

270