inria-00276937, version 1
Applying 3D Human Model in a Posture Recognition System
Bernard Boulay 1François Bremond
1Monique Thonnat 1
Pattern Recognition Letters 27, 15 (2006) 1788-1796
Résumé : This paper proposes an approach to recognise human postures in videosequences, which combines a 2D approach with a 3D human model. The 3D model is a realistic articulated human model which is used to obtain reference postures to compare with test postures. Several 2D approaches using different silhouette representations are compared with each other: projections of moving pixels on the reference axis, Hu moments and skeletonisation. We are interested in a set of specific postures which are representative of typical video understanding applications. We describe results for recognition of general postures (e.g. standing) and detailed postures (e.g standing with one arm up) in ambiguous/optimal viewpoint with good/bad segmented silhouette to show the effectiveness of our approach.
- 1 : ORION (INRIA Sophia Antipolis)
- INRIA
- Domaine : Informatique/Traitement des images
- Mots-clés : Human posture – 3D human model – Vision and image processing – Silhouette – Horizontal and vertical projections – Hu moments – Image skeletonisation
- inria-00276937, version 1
- http://hal.inria.fr/inria-00276937
- oai:hal.inria.fr:inria-00276937
- Contributeur : Francois Bremond
- Soumis le : Lundi 21 Juillet 2008, 11:57:17
- Dernière modification le : Mardi 28 Avril 2009, 17:06:55






Documents associés
Exporter