Unsupervised spatiotemporal video clustering a versatile mean-shift formulation robust to total object occlusions - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Unsupervised spatiotemporal video clustering a versatile mean-shift formulation robust to total object occlusions

Simon Mure
  • Fonction : Auteur
Thomas Grenier
Hugues Benoit-Cattin

Résumé

In this paper, we propose a mean-shift formulation allowing spatiotemporal clustering of video streams, and possibly extensible to other multivariate evolving data. Our formulation enables causal or omniscient filtering of spatiotemporal data, which is robust to total object occlusions. It embeds a new clustering algorithm within the filtering procedure that will group samples and reduce their number over the iterations. Based on our formulation, we express similar approaches and assess their robustness on real video sequences.
Fichier non déposé

Dates et versions

hal-01433000 , version 1 (12-01-2017)

Identifiants

Citer

Simon Mure, Thomas Grenier, Hugues Benoit-Cattin. Unsupervised spatiotemporal video clustering a versatile mean-shift formulation robust to total object occlusions. The 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Mar 2016, Shanghai, China. pp.1536-1540, ⟨10.1109/ICASSP.2016.7471934⟩. ⟨hal-01433000⟩
70 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More