A New Bayesian Modeling for 3D Human-Object Action Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

A New Bayesian Modeling for 3D Human-Object Action Recognition

Résumé

Intelligent surveillance systems in human-centered environments require people behavioral monitoring. In this paper, we propose a new Bayesian framework to recognize actions on RGB-D videos by two different observations: the human pose and objects in its vicinity. We design a model for each action that integrates these observations and a probabilistic sequencing of actions performed during activities. We validate our approach on two public video datasets: CAD-120 and Watch-n-Patch. We show a performance gain of 4% in action detection on the fly on CAD-120 videos. Our approach is competitive to 2D image features and skeleton-based methods, as we present an improvement of 16% on Watch-n-Patch. Action recognition performance is clearly improved by our Bayesian and joint human-object perception.
Fichier principal
Vignette du fichier
Draft_using_AVSS_template.pdf (1.91 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02940714 , version 1 (16-09-2020)

Identifiants

Citer

Camille Maurice, Jorge Francisco Madrigal Diaz, André Monin, Frédéric Lerasle. A New Bayesian Modeling for 3D Human-Object Action Recognition. 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2019), Sep 2019, Taipei, Taiwan. ⟨10.1109/AVSS.2019.8909873⟩. ⟨hal-02940714⟩
76 Consultations
91 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More