Graph Mining for Object Tracking in Videos - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Graph Mining for Object Tracking in Videos

Résumé

This paper shows a concrete example of the use of graph mining for tracking objects in videos with moving cameras and without any contextual information on the objects to track. To make the mining algorithm efficient, we benefit from a video representation based on dy- namic (evolving through time) planar graphs. We then define a number of constraints to efficiently find our so-called spatio-temporal graph pat- terns. Those patterns are linked through an occurrences graph to allow us to tackle occlusion or graph features instability problems in the video. Experiments on synthetic and real videos show that our method is effec- tive and allows us to find relevant patterns for our tracking application.
Fichier principal
Vignette du fichier
pkdd2012.pdf (266.12 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00714705 , version 1 (05-07-2012)
hal-00714705 , version 2 (20-09-2012)

Identifiants

  • HAL Id : hal-00714705 , version 2

Citer

Fabien Diot, Elisa Fromont, Baptiste Jeudy, Emmanuel Marilly, Olivier Martinot. Graph Mining for Object Tracking in Videos. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2012, Bristol, United Kingdom. pp.394-409. ⟨hal-00714705v2⟩
109 Consultations
141 Téléchargements

Partager

Gmail Facebook X LinkedIn More