Effective Surface Normals Based Action Recognition in Depth Images

Xuan Nguyen 1 Thanh Nguyen 2 François Charpillet 1
1 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : In this paper, we propose a new local descriptor for action recognition in depth images. The proposed descriptor relies on surface normals in 4D space of depth, time, spatial coordinates and higher-order partial derivatives of depth values along spatial coordinates. In order to classify actions, we follow the traditional Bag-of-words (BoW) approach, and propose two encoding methods termed Multi-Scale Fisher Vector (MSFV) and Temporal Sparse Coding based Fisher Vector Coding (TSCFVC) to form global representations of depth sequences. The high-dimensional action descriptors resulted from the two encoding methods are fed to a linear SVM for efficient action classification. Our proposed methods are evaluated on two public benchmark datasets, MSRAction3D and MSRGesture3D. The experimental result shows the effectiveness of the proposed methods on both the datasets.
Type de document :
Communication dans un congrès
ICPR 2016 - 23rd International Conference on Pattern Recognition , Dec 2016, Cancun, Mexico. 2016
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01409021
Contributeur : François Charpillet <>
Soumis le : lundi 5 décembre 2016 - 15:59:00
Dernière modification le : jeudi 15 mars 2018 - 16:56:07
Document(s) archivé(s) le : lundi 20 mars 2017 - 18:32:13

Fichier

ICPR_manuscript.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01409021, version 1

Collections

Citation

Xuan Nguyen, Thanh Nguyen, François Charpillet. Effective Surface Normals Based Action Recognition in Depth Images. ICPR 2016 - 23rd International Conference on Pattern Recognition , Dec 2016, Cancun, Mexico. 2016. 〈hal-01409021〉

Partager

Métriques

Consultations de la notice

169

Téléchargements de fichiers

81