Learning Temporally Consistent Rigidities - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Learning Temporally Consistent Rigidities


We present a novel probabilistic framework for rigid tracking and segmentation of shapes observed from multiple cameras. Most existing methods have focused on solving each of these problems individually, segmenting the shape assuming surface registration is solved, or conversely performing surface registration assuming shape segmentation or kinematic structure is known. We assume no prior kinematic or registration knowledge except for an over-estimate k of the number of rigidities in the scene, instead proposing to simultaneously discover, adapt, and track its rigid structure on the fly. We simultaneously segment and infer poses of rigid subcomponents of a single chosen reference mesh acquired in the sequence. We show that this problem can be rigorously cast as a likelihood maximization over rigid component parameters. We solve this problem using an Expectation Maximization algorithm, with latent observation assignements to reference vertices and rigid parts. Our experiments on synthetic and real data show the validity of the method, robustness to noise, and its promising applicability to complex sequences.
Vignette du fichier
lock30-iteration.jpg (247.84 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
paper541.pdf (2.61 Mo) Télécharger le fichier
Vignette du fichier
ballon-outlier.jpeg (96.32 Ko) Télécharger le fichier
CVPR2011-Learning-Temporally-Consistent-Rigidities.mp4 (8.42 Mo) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Video

Dates and versions

inria-00583131 , version 1 (05-04-2011)



Jean-Sébastien Franco, Edmond Boyer. Learning Temporally Consistent Rigidities. CVPR 2011 - IEEE Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. pp.1241-1248, ⟨10.1109/CVPR.2011.5995440⟩. ⟨inria-00583131⟩
357 View
2936 Download



Gmail Facebook Twitter LinkedIn More