Titre :

Motion Segments Decomposition of RGB-D Sequences for Human Behavior Understanding

Auteur(s) :

Devanne, Maxime [Auteur]
Modeling and Analysis of Static and Dynamic Shapes [3D-SAM]
Dipartimento di Sistemi e Informatica [DSI]
Berretti, Stefano [Auteur]
Dipartimento di Sistemi e Informatica [DSI]
Pala, Pietro [Auteur]
Dipartimento di Sistemi e Informatica [DSI]
Wannous, Hazem [Auteur]
Modeling and Analysis of Static and Dynamic Shapes [3D-SAM]
Daoudi, Mohamed [Auteur]
Modeling and Analysis of Static and Dynamic Shapes [3D-SAM]
Bimbo, Alberto [Auteur]
Dipartimento di Sistemi e Informatica [DSI]

Titre de la revue :

Pattern Recognition

Pagination :

222 - 233

Éditeur :

Elsevier

Date de publication :

2017

ISSN :

0031-3203

Mot(s)-clé(s) en anglais :

3D human behavior understanding
temporal modeling
shape space analysis
online activity detection * Corresponding author

Discipline(s) HAL :

Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]

Résumé en anglais : [en]

In this paper, we propose a framework for analyzing and understanding human behavior from depth videos. The proposed solution first employs shape analysis of the human pose across time to decompose the full motion into ...
Lire la suite >In this paper, we propose a framework for analyzing and understanding human behavior from depth videos. The proposed solution first employs shape analysis of the human pose across time to decompose the full motion into short temporal segments representing elementary motions. Then, each segment is characterized by human motion and depth appearance around hand joints to describe the change in pose of the body and the interaction with objects. Finally , the sequence of temporal segments is modeled through a Dynamic Naive Bayes classifier, which captures the dynamics of elementary motions characterizing human behavior. Experiments on four challenging datasets evaluate the potential of the proposed approach in different contexts, including gesture or activity recognition and online activity detection. Competitive results in comparison with state of the art methods are reported.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Plateforme Recherche et Innovation dans les Environnements Visuels Numériques et Interactifs

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL