• français
    • English
    English
  • Ouvrir une session
Aide
Voir le document 
  •   Accueil de SAM
  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
  • Voir le document
  • Accueil de SAM
  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
  • Voir le document
JavaScript is disabled for your browser. Some features of this site may not work without it.

An Efficient Human Activity Recognition Technique Based on Deep Learning

Article dans une revue avec comité de lecture
Auteur
KHELALEF, Aziz
238162 Université Hadj Lakhdar Batna 1
ABABSA, Fakhreddine
543315 Laboratoire d’Ingénierie des Systèmes Physiques et Numériques [LISPEN]
BENOUDJIT, Nabil
238162 Université Hadj Lakhdar Batna 1

URI
http://hdl.handle.net/10985/18281
DOI
10.1134/s1054661819040084
Date
2019
Journal
Распознавание образов и анализ изображе&#1085 / Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications

Résumé

In this paper, we present a new deep learning-based human activity recognition technique. First, we track and extract human body from each frame of the video stream. Next, we abstract human silhouettes and use them to create binary space-time maps (BSTMs) which summarize human activity within a defined time interval. Finally, we use convolutional neural network (CNN) to extract features from BSTMs and classify the activities. To evaluate our approach, we carried out several tests using three public datasets: Weizmann, Keck Gesture and KTH Database. Experimental results show that our technique outperforms conventional state-of-the-art methods in term of recognition accuracy and provides comparable performance against recent deep learning techniques. It’s simple to implement, requires less computing power, and can be used for multi-subject activity recognition.

Fichier(s) constituant cette publication

Nom:
LISPEN_PRIA_ABABSA_2019.pdf
Taille:
2.146Mo
Format:
PDF
Fin d'embargo:
2020-06-29
Voir/Ouvrir

Cette publication figure dans le(s) laboratoire(s) suivant(s)

  • Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)

Documents liés

Visualiser des documents liés par titre, auteur, créateur et sujet.

  • GMCAD: an original Synthetic Dataset of 2D Designs along their Geometrical and Mechanical Conditions 
    Article dans une revue avec comité de lecture
    ALMASRI, Waad; BETTEBGHOR, Dimitri; ADJED, Faouzi; ABABSA, Fakhreddine; ccDANGLADE, Florence (Elsevier BV, 2022)
    We build an original synthetic dataset of 2D mechanical designs alongside their mechanical and geometric constraints, GMCAD. Such a dataset allows training Deep Learning (DL) models for Design for Additive Manufacturing ...
  • Methodology for the Field Evaluation of the Impact of Augmented Reality Tools for Maintenance Workers in the Aeronautic Industry 
    Article dans une revue avec comité de lecture
    LOIZEAU, Quentin; ABABSA, Fakhreddine; ccMERIENNE, Frédéric; ccDANGLADE, Florence (Frontiers, 2021)
    Augmented Reality (AR) enhances the comprehension of complex situations by making the handling of contextual information easier. Maintenance activities in aeronautics consist of complex tasks carried out on various ...
  • Deep Learning Architecture for Topological Optimized Mechanical Design Generation with Complex Shape Criterion 
    Communication avec acte
    ALMASRI, Waad; BETTEBGHOR, Dimitri; ABABSA, Fakhreddine; ADJED, Faouzi; ccDANGLADE, Florence (Springer International Publishing, 2021)
    Topology optimization is a powerful tool for producing an optimal free-form design from input mechanical constraints. However, in its traditional-density-based approach, it does not feature a proper definition for the ...
  • 3D Human Pose Estimation with a Catadioptric Sensor in Unconstrained Environments Using an Annealed Particle Filter 
    Article dans une revue avec comité de lecture
    ABABSA, Fakhreddine; HADJ-ABDELKADER, Hicham; BOUI, Marouane (MDPI, 2020)
    The purpose of this paper is to investigate the problem of 3D human tracking in complex environments using a particle filter with images captured by a catadioptric vision system. This issue has been widely studied in the ...
  • Combining HoloLens and Leap-Motion for Free Hand-Based 3D Interaction in MR Environments 
    Communication avec acte
    ABABSA, Fakhreddine; HE, Junhui; ccCHARDONNET, Jean-Rémy (Springer International Publishing, 2020)
    The ability to interact with virtual objects using gestures would allow users to improve their experience in Mixed Reality (MR) environments, especially when they use AR headsets. Today, MR head-mounted displays like the ...

Parcourir

Tout SAMLaboratoiresAuteursDates de publicationCampus/InstitutsCe LaboratoireAuteursDates de publicationCampus/Instituts

Lettre Diffuser la Science

Dernière lettreVoir plus

Statistiques de consultation

Publications les plus consultéesStatistiques par paysAuteurs les plus consultés

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales

ÉCOLE NATIONALE SUPERIEURE D'ARTS ET METIERS

  • Contact
  • Mentions légales