Projection-based Classification of Surfaces for 3D Human Mesh Sequence Retrieval
| Autor: | Juan Carlos Álvarez Paiva, Mohamed Daoudi, Emery Pierson |
|---|---|
| Přispěvatelé: | Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Laboratoire Paul Painlevé (LPP), Université de Lille-Centre National de la Recherche Scientifique (CNRS), Ecole nationale supérieure Mines-Télécom Lille Douai (IMT Nord Europe), Institut Mines-Télécom [Paris] (IMT), ANR-19-CE23-0020,Human4D,Human4D: Acquisition, Analyse et Synthèse de la Forme du Corps Humain en Mouvement(2019), ANR-16-IDEX-0004,ULNE,ULNE(2016), Laboratoire Paul Painlevé - UMR 8524 (LPP), Centre National de la Recherche Scientifique (CNRS)-Université de Lille |
| Rok vydání: | 2021 |
| Předmět: |
Surface (mathematics)
Unit sphere Computational Geometry (cs.CG) FOS: Computer and information sciences 3D Human Shape Analysis Plane (geometry) Mathematical analysis General Engineering Spherical harmonics 020207 software engineering 02 engineering and technology [INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG] Computer Graphics and Computer-Aided Design spherical harmonics analysis Human-Computer Interaction 4D Human Retrieval Convex geometry Projection (mathematics) Unit vector Line (geometry) 0202 electrical engineering electronic engineering information engineering Computer Science - Computational Geometry 020201 artificial intelligence & image processing Invariant (mathematics) Mathematics |
| Zdroj: | Computers & Graphics: X Computers & Graphics: X, 2022, 102 (45-55) Computers & Graphics: X, 2021, ⟨10.1016/j.cag.2021.10.012⟩ |
| ISSN: | 2590-1486 |
| DOI: | 10.48550/arxiv.2111.13985 |
| Popis: | 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 finitely-triangulated 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|