Human Action Recognition from Body-Part Directional Velocity using Hidden Markov Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Human Action Recognition from Body-Part Directional Velocity using Hidden Markov Models

Résumé

This paper introduces a novel approach for early recognition of human actions using 3D skeleton joints extracted from 3D depth data. We propose a novel, frame-by-frame and real-time descriptor called Body-part Directional Velocity (BDV) calculated by considering the algebraic velocity produced by different body-parts. A real-time Hidden Markov Models algorithm with Gaussian Mixture Models state-output distributions is used to carry out the classification. We show that our method outperforms various state-of-the-art skeleton-based human action recognition approaches on MSRAction3D and Florence3D datasets. We also proved the suitability of our approach for early human action recognition by deducing the decision from a partial analysis of the sequence.
Fichier principal
Vignette du fichier
ICMLA_2017.pdf (960.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01855162 , version 1 (07-08-2018)

Identifiants

Citer

Sid Ahmed Walid Talha, Anthony Fleury, Sebastien Ambellouis. Human Action Recognition from Body-Part Directional Velocity using Hidden Markov Models. 16th IEEE International Conference on Machine Learning and Applications (ICMLA2017), Dec 2017, Cancun, Mexico. ⟨10.1109/ICMLA.2017.00-14⟩. ⟨hal-01855162⟩
70 Consultations
256 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More