Human body part estimation from depth images via spatially-constrained deep learning

Mingyuan Jiu 1 Christian Wolf 1 Graham W. Taylor 2 Atilla Baskurt 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Object recognition, human pose estimation and scene recognition are applications which are frequently solved through a decomposition into a collection of parts. The resulting local representation has significant advantages, especially in the case of occlusions and when the subject is non-rigid. Detection and recognition require modelling the appearance of the different object parts as well as their spatial layout. This representation has been particularly successful in body part estimation from depth images. Integrating the spatial layout of parts may require the minimization of complex energy functions. This 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 spatial layout into parts classification without costly pairwise terms during testing. Spatial relationships are exploited in the training algorithm, but not during testing. As with competing methods, the proposed method classifies pixels independently, which makes real-time processing possible. We show that training a classifier with spatial relationships increases generalization performance when compared to classical training minimizing classification error on the training set. We present an application to human body part estimation from depth images.
Type de document :
Article dans une revue
Pattern Recognition Letters, Elsevier, 2014, 1, 50, pp.122-129
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01269994
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : lundi 27 mars 2017 - 11:22:57
Dernière modification le : jeudi 19 avril 2018 - 14:38:06
Document(s) archivé(s) le : mercredi 28 juin 2017 - 13:03:01

Fichier

Liris-6327.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01269994, version 1

Citation

Mingyuan Jiu, Christian Wolf, Graham W. Taylor, Atilla Baskurt. Human body part estimation from depth images via spatially-constrained deep learning. Pattern Recognition Letters, Elsevier, 2014, 1, 50, pp.122-129. 〈hal-01269994〉

Partager

Métriques

Consultations de la notice

331

Téléchargements de fichiers

178