Computing temporal alignments of human motion sequences in wide clothing using geodesic patches - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Computing temporal alignments of human motion sequences in wide clothing using geodesic patches

Abstract

In this paper, we address the problem of temporal alignment of surfaces for subjects dressed in wide clothing, as acquired by calibrated multi-camera systems. Most existing methods solve the alignment by fitting a single surface template to each instant's 3D observations, relying on a dense point-to-point correspondence scheme, e.g. by matching individual surface points based on local geometric features or proximity. The wide clothing situation yields more geometric and topological difficulties in observed sequences, such as apparent merging of surface components, misreconstructions, and partial surface observation, resulting in overly sparse, erroneous point-to-point correspondences, and thus alignment failures. To resolve these issues, we propose an alignment framework where point-to-point correspondences are obtained by growing isometric patches from a set of reliably obtained body landmarks. This correspondence decreases the reliance on local geometric features subject to instability, instead emphasizing the surface neighborhood coherence of matches, while improving density given sufficient landmark coverage. We validate and verify the resulting improved alignment performance in our experiments.
Fichier principal
Vignette du fichier
clothes_tracking.pdf (8.32 Mo) Télécharger le fichier
Vignette du fichier
templateFitting (1).png (177.95 Ko) Télécharger le fichier
3DV2016VideoLowResolution.mp4 (35.88 Mo) Télécharger le fichier
Vignette du fichier
img.png (237.82 Ko) Télécharger le fichier
Vignette du fichier
templateFitting.png (177.95 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Video
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01367791 , version 1 (08-11-2016)

Licence

Attribution - NonCommercial - NoDerivatives

Identifiers

Cite

Aurela Shehu, Jinlong Yang, Jean-Sébastien Franco, Franck Hétroy-Wheeler, Stefanie Wuhrer. Computing temporal alignments of human motion sequences in wide clothing using geodesic patches. 3DV 2016 - International Conference on 3D Vision 2016, Oct 2016, Stanford, United States. pp.185-193, ⟨10.1109/3DV.2016.27⟩. ⟨hal-01367791⟩
1580 View
291 Download

Altmetric

Share

Gmail Facebook X LinkedIn More