Activity recognition from videos with parallel hypergraph matching on GPUs

Abstract : In this paper, we propose a method for activity recognition from videos based on sparse local features and hypergraph matching. We benefit from special properties of the temporal domain in the data to derive a sequential and fast graph matching algorithm for GPUs. Traditionally, graphs and hypergraphs are frequently used to recognize complex and often non-rigid patterns in computer vision, either through graph matching or point-set matching with graphs. Most formulations resort to the minimization of a difficult discrete energy function mixing geometric or structural terms with data attached terms involving appearance features. Traditional methods solve this minimization problem approximately, for instance with spectral techniques. In this work, instead of solving the problem approximatively, the exact solution for the optimal assignment is calculated in parallel on GPUs. The graphical structure is simplified and regularized, which allows to derive an efficient recursive minimization algorithm. The algorithm distributes subproblems over the calculation units of a GPU, which solves them in parallel, allowing the system to run faster than real-time on medium-end GPUs.
Type de document :
[Research Report] INSA Lyon. 2015
Liste complète des métadonnées

Littérature citée [44 références]  Voir  Masquer  Télécharger
Contributeur : Christian Wolf <>
Soumis le : vendredi 27 novembre 2015 - 11:22:28
Dernière modification le : mercredi 31 octobre 2018 - 12:24:25
Document(s) archivé(s) le : dimanche 28 février 2016 - 11:36:36


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01234661, version 1
  • ARXIV : 1505.00581



Eric Lombardi, Christian Wolf, Oya Celiktutan, Bülent Sankur. Activity recognition from videos with parallel hypergraph matching on GPUs. [Research Report] INSA Lyon. 2015. 〈hal-01234661〉



Consultations de la notice


Téléchargements de fichiers