Titre :

RGBD deep multi-scale network for background subtraction

Auteur(s) :

Houhou, Ihssane [Auteur]
Université Bourgogne Franche-Comté [COMUE] [UBFC]
Université de Technologie de Belfort-Montbeliard [UTBM]
University of Biskra Mohamed Khider
Zitouni, Athmane [Auteur]
University of Biskra Mohamed Khider
Ruichek, Yassine [Auteur]
Université Bourgogne Franche-Comté [COMUE] [UBFC]
Université de Technologie de Belfort-Montbeliard [UTBM]
Connaissance et Intelligence Artificielle Distribuées [Dijon] [CIAD]
Bekhouche, Salah Eddine [Auteur]
Université de Technologie de Belfort-Montbeliard [UTBM]
Université Bourgogne Franche-Comté [COMUE] [UBFC]
Kas, Mohamed [Auteur]
Université de Technologie de Belfort-Montbeliard [UTBM]
Connaissance et Intelligence Artificielle Distribuées [Dijon] [CIAD]
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]

Titre de la revue :

International Journal of Multimedia Information Retrieval

Pagination :

395–407

Éditeur :

Springer

Date de publication :

2022-09

ISSN :

2192-6611

Mot(s)-clé(s) en anglais :

Computer vision
Background subtraction
Deep learning
DMSN
RGBD
Unseen videos
Scene-independent evaluation

Discipline(s) HAL :

Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

This paper proposes a novel deep learning model called deep multi-scale network (DMSN) for background subtraction. This convolutional neural network is built to use RGB color channels and Depth maps as inputs with which ...
Lire la suite >This paper proposes a novel deep learning model called deep multi-scale network (DMSN) for background subtraction. This convolutional neural network is built to use RGB color channels and Depth maps as inputs with which it can fuse semantic and spatial information. In comparison with previous deep learning background subtraction techniques that lack information due to its use of only RGB channels, our RGBD version is able to overcome most of the drawbacks, especially in some particular kinds of challenges. Further, this paper introduces a new protocol for the SBM-RGBD dataset, concerning scene-independent evaluation, dedicated to Deep Learning methods to set up a competitive platform that includes more challenging situations. The proposed method proved its efficiency in solving the background subtraction in complex situations at different levels. The experimental results verify that the proposed work outperforms the state of the art on SBM-RGBD and GSM datasets.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL