Skip to Main content Skip to Navigation
New interface
Conference papers

Graph Mining for Object Tracking in Videos

Abstract : 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.
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Elisa Fromont Connect in order to contact the contributor
Submitted on : Thursday, September 20, 2012 - 3:48:22 PM
Last modification on : Saturday, June 25, 2022 - 10:53:54 AM
Long-term archiving on: : Friday, December 21, 2012 - 3:50:38 AM


Files produced by the author(s)


  • HAL Id : hal-00714705, version 2



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⟩



Record views


Files downloads