Integrating spatial layout of object parts into classification without pairwise terms: application to fast body parts estimation from depth images

Mingyuan Jiu 1 Christian Wolf 1 Atilla Baskurt 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Object recognition or human pose estimation methods often resort to a decomposition into a collection of parts. This local representation has significant advantages, especially in case of occlusions and when the ``object'' is non-rigid. Detection and recognition requires modelling the appearance of the different object parts as well as their spatial layout. The latter can be complex and requires the minimization of complex energy functions, which is prohibitive in most real world applications and therefore often omitted. However, ignoring the spatial layout puts all the burden on the classifier, whose only available information is local appearance. We propose a new method to integrate the spatial layout into the parts classification without costly pairwise terms. We present an application to body parts classification for human pose estimation.As a second contribution, we introduce edge features from RGB images as a complement to the well known depth features used for body parts classification from Kinect data.
Type de document :
Communication dans un congrès
VISAPP, Feb 2013, Barcelona, Spain. pp.626-631, 2013
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01339138
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : mercredi 29 juin 2016 - 15:46:15
Dernière modification le : lundi 10 décembre 2018 - 17:47:39

Identifiants

  • HAL Id : hal-01339138, version 1

Collections

EC-LYON | LIRIS | INSA-LYON | UNIV-LYON1 | LABEXIMU

Citation

Mingyuan Jiu, Christian Wolf, Atilla Baskurt. Integrating spatial layout of object parts into classification without pairwise terms: application to fast body parts estimation from depth images. VISAPP, Feb 2013, Barcelona, Spain. pp.626-631, 2013. 〈hal-01339138〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

130

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD