Titre :

Place Recognition via 3D Modeling for Personal Activity Lifelog Using Wearable Camera

Auteur(s) :

Wannous, Hazem [Auteur]
FOX MIIRE [LIFL]
Dovgalecs, Vladislavs [Auteur]
Laboratoire de l'intégration, du matériau au système [IMS]
Mégret, Rémi [Auteur]
Laboratoire de l'intégration, du matériau au système [IMS]
Daoudi, Mohamed [Auteur]
Institut TELECOM/TELECOM Lille1
FOX MIIRE [LIFL]

Titre de la manifestation scientifique :

International Conference on Multimedia Modeling

Ville :

Klangenfurt

Pays :

Autriche

Date de début de la manifestation scientifique :

2012-01-04

Titre de l’ouvrage :

International Conference on Multimedia Modeling

Date de publication :

2012

Mot(s)-clé(s) en anglais :

Activity Lifelog
3D Place recognition
Wearable Camera

Discipline(s) HAL :

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

Résumé en anglais : [en]

In this paper, a method for location recognition in a visual lifelog is presented. Its motivation is the detection of activity related places within an indoor environment to facilitate navigation in the lifelog. It takes ...
Lire la suite >In this paper, a method for location recognition in a visual lifelog is presented. Its motivation is the detection of activity related places within an indoor environment to facilitate navigation in the lifelog. It takes advantage of a camera mounted on the shoulder, which is pri- marily designed for the behavioral analysis of Instrumental Activities of Daily Living (IADL). The proposed approach provides an automatic in- dexing of the content stream, based on the presence in specific 3D places related to instrumental activites. It relies on 3D models of the places of interest that are built thanks to a lightweight semi-supervised approach. Performance evaluation on real data show the potential of this approach compared to 2D only recognition.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Commentaire :

11 Pages

Collections :

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

Source :

Harvested from HAL