Coherent Laplacian 3-D Protrusion Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Coherent Laplacian 3-D Protrusion Segmentation


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.
Fichier principal
Vignette du fichier
CuzzolinCVPR08.pdf (1.04 Mo) Télécharger le fichier
Vignette du fichier
finalsegm-erwan99-s2d5k12-2.png (27.65 Ko) Télécharger le fichier
Vignette du fichier
finaltraj-erwan7199-s2d5k12-2.png (43.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Figure, Image

Dates and versions

inria-00590250 , version 1 (03-05-2011)



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. pp.1-8, ⟨10.1109/CVPR.2008.4587452⟩. ⟨inria-00590250⟩
220 View
182 Download



Gmail Facebook X LinkedIn More