Projection-based Classification of Surfaces for 3D Human Mesh Sequence Retrieval

Pierson, Emery; Alvarez-Paiva, Juan Carlos; Daoudi, Mohamed

Type de document :

Article dans une revue scientifique: Article original

Titre :

Projection-based Classification of Surfaces for 3D Human Mesh Sequence Retrieval

Auteur(s) :

Pierson, Emery [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Alvarez-Paiva, Juan Carlos [Auteur]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Daoudi, Mohamed [Auteur]

Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Titre de la revue :

Computers & Graphics: X

Éditeur :

Elsevier

Date de publication :

2022-02-01

ISSN :

2590-1486

Mot(s)-clé(s) en anglais :

3D Human Shape Analysis
4D Human Retrieval
Convex geometry
spherical harmonics analysis

Discipline(s) HAL :

Informatique [cs]/Géométrie algorithmique [cs.CG]

Résumé en anglais : [en]

We analyze human poses and motion by introducing three sequences of easily calculated surface descriptors that are invariant under reparametrizations and Euclidean transformations. These descriptors are obtained by associating ...
Lire la suite >We analyze human poses and motion by introducing three sequences of easily calculated surface descriptors that are invariant under reparametrizations and Euclidean transformations. These descriptors are obtained by associating to each finitelytriangulated surface two functions on the unit sphere: for each unit vector u we compute the weighted area of the projection of the surface onto the plane orthogonal to u and the length of its projection onto the line spanned by u. The L 2 norms and inner products of the projections of these functions onto the space of spherical harmonics of order k provide us with three sequences of Euclidean and reparametrization invariants of the surface. The use of these invariants reduces the comparison of 3D+time surface representations to the comparison of polygonal curves in R n. The experimental results on the FAUST and CVSSP3D artificial datasets are promising. Moreover, a slight modification of our method yields good results on the noisy CVSSP3D real dataset.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Human4D: Acquisition, Analyse et Synthèse de la Forme du Corps Humain en Mouvement
ULNE

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Projection-based Classification of Surfaces ... BibTeX CSV Excel RIS

Projection-based Classification of Surfaces ...

BibTeX

CSV

Excel

RIS